├── 深度长尾学习综述.pdf ├── 资源 ├── 图片 │ ├── fig1.pdf │ ├── fig2.pdf │ ├── fig3.pdf │ └── fig4.pdf ├── 表格 │ ├── table4.tex │ ├── table1.tex │ ├── table3.tex │ ├── table7.tex │ ├── table5_6.tex │ └── table2.tex └── 参考文献 │ ├── references.txt │ └── references.bib ├── LICENSE └── README.md /深度长尾学习综述.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jorwnpay/A-Long-Tailed-Survey/HEAD/深度长尾学习综述.pdf -------------------------------------------------------------------------------- /资源/图片/fig1.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jorwnpay/A-Long-Tailed-Survey/HEAD/资源/图片/fig1.pdf -------------------------------------------------------------------------------- /资源/图片/fig2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jorwnpay/A-Long-Tailed-Survey/HEAD/资源/图片/fig2.pdf -------------------------------------------------------------------------------- /资源/图片/fig3.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jorwnpay/A-Long-Tailed-Survey/HEAD/资源/图片/fig3.pdf -------------------------------------------------------------------------------- /资源/图片/fig4.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Jorwnpay/A-Long-Tailed-Survey/HEAD/资源/图片/fig4.pdf -------------------------------------------------------------------------------- /资源/表格/table4.tex: -------------------------------------------------------------------------------- 1 | \begin{table}[htbp] 2 | \small 3 | \centering 4 | \captionsetup{font=footnotesize} 5 | \caption{分类器总结，其中$w,f,b,\phi$和$p$分别表示模型分类器、样本特征、 6 | 偏差项、softmax函数和预测概率。此外，$\hat{d}$是指数移动平均特征的单位向量。 7 | 温度因子用$\tau$表示，其他与分类器相关的超参数包括$\gamma$和$\alpha$。} 8 | \begin{tabular}{lc} 9 | \toprule 10 | 分类器 & 表达式 \\ 11 | \midrule 12 | 线性分类器 & $p=\phi(w^\top f+b)$ \\ 13 | 余弦分类器 & $p=\phi(\tau \frac{w^\top f}{\Vert w \Vert \Vert f \Vert}+b)$ \\ 14 | $\tau$-归一化分类器 & $p=\phi(\frac{w^\top f}{\Vert w \Vert^{\tau}_2}+b)$ \\ 15 | 因果分类器 & $p=\phi(\tau \frac{(w)^{\top} f}{(\Vert w \Vert + \gamma)\Vert f \Vert} 16 | - \alpha \frac{cos(x,\hat{d})(w)^{\top}\hat{d}}{\Vert w \Vert + \gamma})$ \\ 17 | \bottomrule 18 | \end{tabular}% 19 | \label{tab:addlabel}% 20 | \end{table}% -------------------------------------------------------------------------------- /资源/表格/table1.tex: -------------------------------------------------------------------------------- 1 | \begin{table}[htbp] 2 | \scriptsize 3 | \centering 4 | \captionsetup{font=footnotesize} 5 | \caption{\textbf{长尾数据集统计。“Cls.”表示图像分类；“Det.”表示目标检测；“Seg.”表示实例分割。}} 6 | \begin{tabular}{llccc} 7 | \toprule 8 | 任务 & 数据集 & \# 类别 & \# 训练数据 & \# 测试数据 \\ 9 | \midrule 10 | \multirow{4}[2]{*}{Cls.} & ImageNet-LT \cite{Liu_2019} & 1,000 & 115,846 & 50,000 \\ 11 | & CIFAR100-LT \cite{cao2019learning} & 100 & 50,000 & 10,000 \\ 12 | & Places-LT \cite{Liu_2019} & 365 & 62,500 & 36,500 \\ 13 | & iNaturalist 2018 \cite{Van_Horn_2018} & 8,142 & 437,513 & 24,426 \\ 14 | \midrule 15 | \multirow{2}[2]{*}{Det./Seg.} & LVIS v0.5 \cite{Gupta_2019} & 1,230 & 57,000 & 20,000 \\ 16 | & LVIS v1 \cite{Gupta_2019} & 1,203 & 100,000 & 19,800 \\ 17 | \midrule 18 | \multirow{2}[2]{*}{多标签 Cls.} & VOC-LT \cite{Wu_2020_dist} & 20 & 1,142 & 4,952 \\ 19 | & COCO-LT \cite{Wu_2020_dist} & 80 & 1,909 & 5,000 \\ 20 | \midrule 21 | 视频 Cls. & VideoLT \cite{Zhang_2021_video} & 1,004 & 179,352 & 51,244 \\ 22 | \bottomrule 23 | \end{tabular}% 24 | \label{tab:1}% 25 | \end{table}% -------------------------------------------------------------------------------- /资源/表格/table3.tex: -------------------------------------------------------------------------------- 1 | \begin{table}[htbp] 2 | \small 3 | \centering 4 | \captionsetup{font=footnotesize} 5 | \caption{损失函数总结。在该表中，$z$和$p$表示样本$x$的预测logits和softmax概率， 6 | 其中$z_y$和$p_y$对应于类别$y$。此外，$n$表示训练数据的总数，其中$n_y$是类别$y$的样本数。 7 | 此外，$\pi$表示采样频率的向量，其中$\pi_y=n_y/n$表示类别$y$的标签频率。 8 | 若没有给出更具体的值，类别权重由$w$表示，类别边距由$\Delta$表示。损失相关参数包括$\gamma$。} 9 | \begin{tabular}{ll} 10 | \toprule 11 | 损失 & 表达式 \\ 12 | \midrule 13 | Softmax 损失 & $\mathcal{L}_{ce}=-log(p_y)$ \\ 14 | 加权 Softmax 损失 & $\mathcal{L}_{wce}=-\frac{1}{\pi_y}log(p_y)$ \\ 15 | 焦点损失 \cite{Lin_2017_focal} & $\mathcal{L}_{fl}=-(1-p_y)^\gamma log(p_y)$ \\ 16 | 类别平衡损失 \cite{Cui_2019} & $\mathcal{L}_{cb}=-\frac{1-\gamma}{1-\gamma^{n_y}}log(p_y)$ \\ 17 | 平衡 Softmax 损失 \cite{ren2020balanced} & $\mathcal{L}_{bs}=-log(\frac{\pi_y exp(z_y)}{\sum_j \pi_j exp(z_j)})$ \\ 18 | 均衡损失 \cite{Tan_2020} & $\mathcal{L}_{eq}=-log(\frac{exp(z_y)}{\sum_j w_j exp(z_j)})$ \\ 19 | LDAM 损失 \cite{cao2019learning} & $\mathcal{L}_{ldam}=-log(\frac{exp(z_y-\Delta_y)}{\sum_j exp(z_j-\Delta_j)})$ \\ 20 | \bottomrule 21 | \end{tabular}% 22 | \label{tab:3}% 23 | \end{table}% -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2023 Wenpei Jiao 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ## 深度长尾学习综述 2 | 3 | ### 1. 项目介绍 4 | 5 | 在过去的十年中，深度学习已经成为学习高质量图像表示的强大识别模型，并在通用视觉识别上取得了显著突破。然而，长尾类别不平衡是实际视觉识别任务中的一个常见问题，它常常限制了基于深度网络的识别模型在实际应用中的实用性，因为它们很容易偏向于多数类，而在尾部类上的性能很差。为了解决这个问题，近年来进行了大量的研究，在深度长尾学习领域取得了可喜的进展。 6 | 7 | 2021年颜水成团队发了一篇关于深度长尾学习的综述文章：[Deep Long-Tailed Learning: A Survey](https://arxiv.org/abs/2110.04596)，以总结这一领域的进展。这篇文章是长尾学习领域第一篇系统综述，非常值得阅读。 8 | 9 | 因为这篇文章篇幅较长，通读需要花费很长时间；而很多同学只是在具体的任务中遇到了长尾问题，比如图神经网络、声纳图像识别、医学图像分割等，这时候去网上找相关资料需要花费大量时间，而且通常找到的资料不系统、不全面。对于英语不太好的同学来说，在阅读英文论文时就失去了快速浏览的能力，难以对一篇文章的主要内容快速把握。 10 | 11 | 因此，本项目完整翻译了这篇综述文章：[Deep Long-Tailed Learning: A Survey](https://arxiv.org/abs/2110.04596)，希望能对想了解长尾学习的同学有所帮助。 12 | 13 | ### 2. 资源 14 | 15 | 本项目开放了： 16 | 17 | 1）中文版的《深度长尾学习：综述》.pdf文件； 18 | 19 | 2）文中图片的.pdf原图； 20 | 21 | 3）表格的latex代码； 22 | 23 | 4）参考文献的.bib和.txt文件； 24 | 25 | 以方便读者使用。 26 | 27 | ### 3. 引用 28 | 29 | 如果你的工作中用到了这篇论文的内容，请引用英文原文（顺便点个:star:！:blush:）。 30 | 31 | ``` 32 | @article{zhang2021deep, 33 | title={Deep long-tailed learning: A survey}, 34 | author={Zhang, Yifan and Kang, Bingyi and Hooi, Bryan and Yan, Shuicheng and Feng, Jiashi}, 35 | journal={arXiv preprint arXiv:2110.04596}, 36 | year={2021} 37 | } 38 | ``` 39 | 40 | 41 | 42 | -------------------------------------------------------------------------------- /资源/表格/table7.tex: -------------------------------------------------------------------------------- 1 | \begin{table}[htbp] 2 | \footnotesize 3 | \centering 4 | \captionsetup{font=footnotesize} 5 | \caption{在ImageNet-LT上进行解耦训练200个周期得到的各种代价敏感损失的性能结果。 6 | 这里，“Joint”表示单阶段的端到端联合训练；“NCM”是最近类别均值分类器\cite{kang2019decoupling}；“CRT” 7 | 表示类别平衡分类器再训练\cite{kang2019decoupling}； 8 | “LWS”是指可学习权值缩放\cite{kang2019decoupling}。此外，BS表示 9 | 平衡softmax方法\cite{ren2020balanced}。} 10 | \resizebox{3.5in}{!}{ 11 | \begin{tabular}{lccccccccc} 12 | \toprule 13 | \multirow{2}[4]{*}{Test Dist.} & \multicolumn{4}{c}{所有类准确度} & & \multicolumn{4}{c}{头部类准确度} \\ 14 | \cmidrule{2-5}\cmidrule{7-10} & Joint & NCM & CRT & LWS & & Joint & NCM & CRT & LWS \\ 15 | \midrule 16 | Softmax & 46.8 & 50.2 & 50.2 & 50.8 & & 66.9 & 63.5 & 65.0 & 64.6 \\ 17 | 焦点损失 \cite{Lin_2017_focal} & 47.2 & 50.7 & 50.7 & 51.5 & & 67.0 & 62.6 & 64.5 & 64.3 \\ 18 | ESQL \cite{Tan_2020} & 48.0 & 49.8 & 50.6 & 50.5 & & 63.1 & 60.2 & 64.0 & 63.3 \\ 19 | BS \cite{ren2020balanced} & 51.2 & 50.4 & 50.6 & 51.1 & & 62.4 & 62.4 & 64.9 & 64.3 \\ 20 | \midrule 21 | \midrule 22 | \multirow{2}[4]{*}{Test Dist.} & \multicolumn{4}{c}{中间类准确度} & & \multicolumn{4}{c}{尾部类准确度} \\ 23 | \cmidrule{2-5}\cmidrule{7-10} & Joint & NCM & CRT & LWS & & Joint & NCM & CRT & LWS \\ 24 | \midrule 25 | Softmax & 40.4 & 45.8 & 45.3 & 46.1 & & 12.6 & 28.1 & 25.5 & 28.2 \\ 26 | 焦点损失 \cite{Lin_2017_focal} & 41.0 & 47.0 & 46.4 & 47.3 & & 13.1 & 30.1 & 26.9 & 30.2 \\ 27 | ESQL \cite{Tan_2020} & 44.6 & 46.6 & 46.5 & 46.1 & & 17.2 & 31.1 & 27.1 & 29.5 \\ 28 | BS \cite{ren2020balanced} & 47.7 & 46.8 & 46.1 & 46.7 & & 32.1 & 29.1 & 26.2 & 29.4 \\ 29 | \bottomrule 30 | \end{tabular}}% 31 | \label{tab:addlabel}% 32 | \end{table}% -------------------------------------------------------------------------------- /资源/表格/table5_6.tex: -------------------------------------------------------------------------------- 1 | \begin{table*}[!t] 2 | \centering 3 | 4 | \begin{minipage}[t]{0.48\textwidth} 5 | \makeatletter\def\@captype{table} 6 | \footnotesize 7 | \centering 8 | \captionsetup{font=footnotesize} 9 | \caption{在ImageNet-LT上训练90或200个周期的准确度（Acc）、较高的参考精度（UA）、 10 | 相对准确度（RA）结果。在该表中，CR、IA和MI分别表示类别重平衡、信息增强和模块改进。} 11 | \resizebox{!}{3.9cm}{ 12 | \begin{tabular}{llccccccc} 13 | \toprule 14 | \multicolumn{1}{l}{\multirow{2}[4]{*}{类型}} & \multirow{2}[4]{*}{方法} & \multicolumn{3}{c}{90 epochs } & & \multicolumn{3}{c}{200 epochs} \\ 15 | \cmidrule{3-5}\cmidrule{7-9} & & Acc & UA & RA & & Acc & UA & RA \\ 16 | \midrule 17 | \multicolumn{1}{l}{基线} & Softmax & 45.5 & 57.3 & 79.4 & & 46.8 & 57.8 & 81.0 \\ 18 | \midrule 19 | \multicolumn{1}{c}{\multirow{7}[2]{*}{CR}} & 加权 Softmax & 47.9 & 57.3 & 83.6 & & 49.1 & 57.8 & 84.9 \\ 20 | & 焦点损失 \cite{Lin_2017_focal} & 45.8 & 57.3 & 79.9 & & 47.2 & 57.8 & 81.7 \\ 21 | & LDAM \cite{cao2019learning} & 51.1 & 57.3 & 89.2 & & 51.1 & 57.8 & 88.4 \\ 22 | & ESQL \cite{Tan_2020} & 47.3 & 57.3 & 82.5 & & 48.0 & 57.8 & 83.0 \\ 23 | & UNO-IC \cite{tian2020posterior} & 45.7 & 57.3 & 81.4 & & 46.8 & 58.6 & 79.9 \\ 24 | & 平衡 Softmax \cite{ren2020balanced} & 50.8 & 57.3 & 88.7 & & 51.2 & 57.8 & 88.6 \\ 25 | & LADE \cite{Hong_2021} & 51.5 & 57.8 & 89.1 & & 51.6 & 57.8 & 89.3 \\ 26 | \midrule 27 | \multicolumn{1}{c}{\multirow{2}[2]{*}{IA}} & SSP \cite{yang2020rethinking} & 53.1 & 59.6 & 89.1 & & 53.3 & 59.9 & 89.0 \\ 28 | & RSG \cite{Wang_2021_rsg} & 49.6 & 57.3 & 86.7 & & 52.9 & 57.8 & 91.5 \\ 29 | \midrule 30 | \multicolumn{1}{c}{\multirow{13}[6]{*}{MI}} & OLTR \cite{Liu_2019} & 46.7 & 57.3 & 81.5 & & 48.0 & 58.4 & 82.2 \\ 31 | & PaCo \cite{Cui_2021} & 52.7 & 58.7 & 89.9 & & 54.4 & 59.6 & 91.3 \\ 32 | & De-confound \cite{tang2020long} & 51.8 & 57.7 & 89.8 & & 51.3 & 57.8 & 88.8 \\ 33 | \cmidrule{2-9} & Decouple-IB-CRT \cite{kang2019decoupling} & 49.9 & 57.3 & 87.1 & & 50.3 & 58.1 & 86.6 \\ 34 | & Decouple-CB-CRT \cite{kang2019decoupling} & 44.9 & 57.3 & 78.4 & & 43.0 & 57.8 & 74.4 \\ 35 | & Decouple-SR-CRT \cite{kang2019decoupling} & 49.3 & 57.3 & 86.0 & & 48.5 & 57.8 & 83.9 \\ 36 | & Decouple-PB-CRT \cite{kang2019decoupling} & 48.4 & 57.3 & 84.5 & & 48.1 & 57.8 & 83.2 \\ 37 | & MiSLAS \cite{Zhong_2021} & 51.4 & 58.3 & 88.2 & & 53.4 & 59.7 & 89.4 \\ 38 | \cmidrule{2-9} & BBN \cite{Zhou_2020} & 41.2 & 57.3 & 71.9 & & 44.7 & 57.8 & 77.3 \\ 39 | & LFME \cite{Xiang_2020} & 47.0 & 57.3 & 82.0 & & 48.0 & 57.8 & 83.0 \\ 40 | & ResLT \cite{Cui_2022} & 51.6 & 57.3 & 90.1 & & 53.2 & 58.1 & 91.6 \\ 41 | & RIDE \cite{wang2020long} & 55.5 & 60.2 & 92.2 & & 56.1 & 60.9 & 92.1 \\ 42 | & TADE \cite{zhang2021test} & \textbf{57.3} & \textbf{61.9} & \textbf{92.6} & & \textbf{58.8} & \textbf{63.2} & \textbf{93.0} \\ 43 | \bottomrule 44 | \end{tabular}}% 45 | \label{tab:5}% 46 | \end{minipage} 47 | \begin{minipage}[t]{0.48\textwidth} 48 | \makeatletter\def\@captype{table} 49 | \footnotesize 50 | \centering 51 | \captionsetup{font=footnotesize} 52 | \caption{在ImageNet-LT上训练90或200个周期得到的头部类、中间类、尾部类的准确度（Acc）结果。 53 | 在该表中，WS表示加权softmax，BS表示平衡softmax。方法的类型与表5相同。} 54 | \resizebox{!}{3.9cm}{ 55 | \begin{tabular}{lccccccc} 56 | \toprule 57 | \multirow{2}[4]{*}{方法} & \multicolumn{3}{c}{90 epochs } & & \multicolumn{3}{c}{200 epochs} \\ 58 | \cmidrule{2-4}\cmidrule{6-8} & 头部 & 中间 & 尾部 & & 头部 & 中间 & 尾部 \\ 59 | \midrule 60 | Softmax & 66.5 & 39.0 & 8.6 & & 66.9 & 40.4 & 12.6 \\ 61 | \midrule 62 | WS & 66.3 & 42.2 & 15.6 & & 57.9 & 46.2 & 34.0 \\ 63 | 焦点损失 \cite{Lin_2017_focal} & 66.9 & 39.2 & 9.2 & & 67.0 & 41.0 & 13.1 \\ 64 | LDAM \cite{cao2019learning} & 62.3 & 47.4 & 32.5 & & 60.0 & 49.2 & 31.9 \\ 65 | ESQL \cite{Tan_2020} & 62.5 & 44.0 & 15.7 & & 63.1 & 44.6 & 17.2 \\ 66 | UNO-IC \cite{tian2020posterior} & 66.3 & 38.7 & 9.3 & & 67.0 & 40.3 & 12.7 \\ 67 | BS \cite{ren2020balanced} & 61.7 & 48.0 & 29.9 & & 62.4 & 47.7 & 32.1 \\ 68 | LADE \cite{Hong_2021} & 62.2 & 48.6 & 31.8 & & 63.1 & 47.7 & 32.7 \\ 69 | \midrule 70 | SSP \cite{yang2020rethinking} & 65.6 & 49.6 & 30.3 & & 67.3 & 49.1 & 28.3 \\ 71 | RSG \cite{Wang_2021_rsg} & \textbf{68.7} & 43.7 & 16.2 & & 65.0 & 49.4 & 31.1 \\ 72 | \midrule 73 | OLTR \cite{Liu_2019} & 58.2 & 45.5 & 19.5 & & 62.9 & 44.6 & 18.8 \\ 74 | PaCo \cite{Cui_2021} & 59.7 & 51.7 & 36.6 & & 63.2 & 51.6 & 39.2 \\ 75 | De-confound \cite{tang2020long} & 63.0 & 48.5 & 31.4 & & 64.9 & 46.9 & 28.1 \\ 76 | \midrule 77 | IB-CRT \cite{kang2019decoupling} & 62.6 & 46.2 & 26.7 & & 64.2 & 46.1 & 26.0 \\ 78 | CB-CRT \cite{kang2019decoupling} & 62.4 & 39.3 & 14.9 & & 60.9 & 36.9 & 13.5 \\ 79 | SR-CRT \cite{kang2019decoupling} & 64.1 & 43.9 & 19.5 & & 66.0 & 42.3 & 18.0 \\ 80 | PB-CRT \cite{kang2019decoupling} & 63.9 & 45.0 & 23.2 & & 64.9 & 43.1 & 20.6 \\ 81 | MiSLAS \cite{Zhong_2021} & 62.1 & 48.9 & 32.6 & & 65.3 & 50.6 & 33.0 \\ 82 | \midrule 83 | BBN \cite{Zhou_2020} & 40.0 & 43.3 & 40.8 & & 43.3 & 45.9 & \textbf{43.7} \\ 84 | LFME \cite{Xiang_2020} & 60.6 & 43.5 & 22.0 & & 64.1 & 42.3 & 22.8 \\ 85 | ResLT \cite{Cui_2022} & 57.8 & 50.4 & 40.0 & & 61.6 & 51.4 & 38.8 \\ 86 | RIDE \cite{wang2020long} & 66.9 & 52.3 & 34.5 & & \textbf{67.9} & 52.3 & 36.0 \\ 87 | TADE \cite{zhang2021test} & 65.3 & \textbf{55.2} & \textbf{42.0} & & 67.2 & \textbf{55.3} & 40.0 \\ 88 | \bottomrule 89 | \end{tabular}}% 90 | \label{tab:6}% 91 | \end{minipage} 92 | % \end{minipage} 93 | 94 | \end{table*} -------------------------------------------------------------------------------- /资源/表格/table2.tex: -------------------------------------------------------------------------------- 1 | \begin{table*}[htbp] 2 | \scriptsize 3 | \centering 4 | \captionsetup{font=footnotesize} 5 | \caption{2021年年中之前在顶级会议上发布的现有深度长尾学习方法总结。主要有三类： 6 | 类别重平衡、信息增强和模块改进。在本表中，“CSL”表示代价敏感学习；“LA”表示logit调整； 7 | “TL”代表迁移学习；“Aug”表示数据增强；“RL”表示表征学习；“CD”表示分类器设计，旨在为长尾 8 | 识别设计新的分类器或预测方案；“DT”表示解耦训练，其中特征提取器和分类器分别进行训练； 9 | “Ensemble”表示基于集成学习的方法。我们还开源了我们收集的长尾学习资源： 10 | \href{https://github.com/Vanint/Awesome-LongTailed-Learning}{https://github.com/Vanint/Awesome-LongTailed-Learning}} 11 | \resizebox{\textwidth}{!}{ 12 | \begin{tabular}{lccccccccccccc} 13 | \toprule 14 | \multirow{2}[4]{*}{Method} & \multirow{2}[4]{*}{ Publication} & \multirow{2}[4]{*}{Year} & \multicolumn{3}{c}{Class Re-balancing} & & \multicolumn{2}{c}{Augmentation} & & \multicolumn{4}{c}{Module Improvement} \\ 15 | \cmidrule{4-6}\cmidrule{8-9}\cmidrule{11-14} & & & Re-sampling & CSL & LA & & TL & Aug & & RL & CD & DT & Ensemble \\ 16 | \midrule 17 | LMLE \cite{Huang_2016} & CVPR & 2016 & √ & & & & & & & √ & & & \\ 18 | HFL \cite{Ouyang_2016} & CVPR & 2016 & & & & & & & & √ & & & \\ 19 | Focal loss \cite{Lin_2017_focal} & ICCV & 2017 & & √ & & & & & & & & & \\ 20 | Range loss \cite{Zhang_2017} & ICCV & 2017 & & & & & & & & √ & & & \\ 21 | CRL \cite{Dong_2017} & ICCV & 2017 & & & & & & & & √ & & & \\ 22 | MetaModelNet \cite{wang2017learning} & NeurIPS & 2017 & & & & & √ & & & & & & \\ 23 | DSTL \cite{Cui_2018} & CVPR & 2018 & & & & & √ & & & & & & \\ 24 | CB \cite{Cui_2019} & CVPR & 2019 & & √ & & & & & & & & & \\ 25 | Bayesian estimate \cite{Khan_2019} & CVPR & 2019 & & √ & & & & & & & & & \\ 26 | FTL \cite{Yin_2019} & CVPR & 2019 & & & & & √ & √ & & & & & \\ 27 | Unequal-training \cite{Zhong_2019} & CVPR & 2019 & & & & & & & & √ & & & \\ 28 | OLTR \cite{Liu_2019} & CVPR & 2019 & & & & & & & & √ & & & \\ 29 | DCL \cite{Wang_2019} & ICCV & 2019 & √ & & & & & & & & & & \\ 30 | Meta-Weight-Net \cite{shu2019meta} & NeurIPS & 2019 & & √ & & & & & & & & & \\ 31 | LDAM \cite{cao2019learning} & NeurIPS & 2019 & & √ & & & & & & & & & \\ 32 | Decoupling \cite{kang2019decoupling} & ICLR & 2020 & √ & √ & & & & & & √ & √ & √ & \\ 33 | LST \cite{Hu_2020} & CVPR & 2020 & √ & & & & √ & & & & & & \\ 34 | BBN \cite{Zhou_2020} & CVPR & 2020 & √ & & & & & & & & & & √ \\ 35 | BAGS \cite{Li_2020} & CVPR & 2020 & √ & & & & & & & & & & √ \\ 36 | Domain adaptation \cite{Jamal_2020} & CVPR & 2020 & & √ & & & & & & & & & \\ 37 | Equalization loss (ESQL) \cite{Tan_2020} & CVPR & 2020 & & √ & & & & & & & & & \\ 38 | DBM \cite{Cao_2020} & CVPR & 2020 & & √ & & & & & & & & & \\ 39 | M2m \cite{Kim_2020_m2m} & CVPR & 2020 & & & & & √ & √ & & & & & \\ 40 | LEAP \cite{Liu_2020} & CVPR & 2020 & & & & & √ & √ & & √ & & & \\ 41 | IEM \cite{Zhu_2020} & CVPR & 2020 & & & & & & & & √ & & & \\ 42 | SimCal \cite{Wang_2020} & ECCV & 2020 & √ & & & & & & & & & √ & √ \\ 43 | PRS \cite{Kim_2020_im} & ECCV & 2020 & √ & & & & & & & & & & \\ 44 | Distribution-balanced loss \cite{Wu_2020_dist} & ECCV & 2020 & & √ & & & & & & & & & \\ 45 | OFA \cite{Chu_2020} & ECCV & 2020 & & & & & √ & √ & & & & √ & \\ 46 | LFME \cite{Xiang_2020} & ECCV & 2020 & & & & & √ & & & & & & √ \\ 47 | Deep-RTC \cite{Wu_2020_solv} & ECCV & 2020 & & & & & & & & & √ & & \\ 48 | Balanced Meta-Softmax \cite{ren2020balanced} & NeurIPS & 2020 & √ & √ & & & & & & & & & \\ 49 | UNO-IC \cite{tian2020posterior} & NeurIPS & 2020 & & & √ & & & & & & & & \\ 50 | De-confound-TDE \cite{tang2020long} & NeurIPS & 2020 & & & √ & & & & & & √ & & \\ 51 | SSP \cite{yang2020rethinking} & NeurIPS & 2020 & & & & & √ & & & √ & & & \\ 52 | Logit adjustment \cite{menon2020long} & ICLR & 2021 & & & √ & & & & & & & & \\ 53 | RIDE \cite{wang2020long} & ICLR & 2021 & & & & & √ & & & & & & √ \\ 54 | KCL \cite{kang2020exploring} & ICLR & 2021 & & & & & & & & √ & & √ & \\ 55 | LTML \cite{Guo_2021} & CVPR & 2021 & √ & & & & & & & & & & √ \\ 56 | Equalization loss v2 \cite{Tan_2021} & CVPR & 2021 & & √ & & & & & & & & & \\ 57 | Seesaw loss \cite{Wang_2021_seesaw} & CVPR & 2021 & & √ & & & & & & & & & \\ 58 | ACSL \cite{Wang_2021_adap} & CVPR & 2021 & & √ & & & & & & & & & \\ 59 | PML \cite{Deng_2021} & CVPR & 2021 & & √ & & & & & & & & & \\ 60 | LADE \cite{Hong_2021} & CVPR & 2021 & & √ & √ & & & & & & & & \\ 61 | RoBal \cite{Wu_2021_adve} & CVPR & 2021 & & √ & √ & & & & & & √ & & \\ 62 | DisAlign \cite{Zhang_2021_distr} & CVPR & 2021 & & √ & √ & & & & & & & √ & \\ 63 | MiSLAS \cite{Zhong_2021} & CVPR & 2021 & & √ & & & & √ & & & & √ & \\ 64 | CReST \cite{Wei_2021} & CVPR & 2021 & & & & & √ & & & & & & \\ 65 | Conceptual 12M \cite{Changpinyo_2021} & CVPR & 2021 & & & & & √ & & & & & & \\ 66 | RSG \cite{Wang_2021_rsg} & CVPR & 2021 & & & & & √ & √ & & & & & \\ 67 | MetaSAug \cite{Li_2021_meta} & CVPR & 2021 & & & & & & √ & & & & & \\ 68 | Hybrid \cite{Wang_2021_cons} & CVPR & 2021 & & & & & & & & √ & & & \\ 69 | Unsupervised discovery \cite{Weng_2021} & CVPR & 2021 & & & & & & & & √ & & & \\ 70 | VideoLT \cite{Zhang_2021_video} & ICCV & 2021 & √ & & & & & & & & & & \\ 71 | LOCE \cite{Feng_2021} & ICCV & 2021 & √ & √ & & & & & & & & & \\ 72 | GIST \cite{Liu_2021} & ICCV & 2021 & √ & & & & √ & & & & √ & & \\ 73 | FASA \cite{Zang_2021} & ICCV & 2021 & √ & & & & & √ & & & & & \\ 74 | ACE \cite{Cai_2021} & ICCV & 2021 & √ & & & & & & & & & & √ \\ 75 | IB \cite{Park_2021} & ICCV & 2021 & & √ & & & & & & & & & \\ 76 | DARS \cite{He_2021_redis} & ICCV & 2021 & & & & & √ & & & & & & \\ 77 | SSD \cite{Li_2021_self} & ICCV & 2021 & & & & & √ & & & & & & \\ 78 | DiVE \cite{He_2021_dist} & ICCV & 2021 & & & & & √ & & & & & & \\ 79 | MosaicOS \cite{Zhang_2021_mosa} & ICCV & 2021 & & & & & √ & & & & & & \\ 80 | PaCo \cite{Cui_2021} & ICCV & 2021 & & & & & & & & √ & & & \\ 81 | DRO-LT \cite{Samuel_2021} & ICCV & 2021 & & & & & & & & √ & & & \\ 82 | DT2 \cite{Desai_2021} & ICCV & 2021 & & & & & & & & & & √ & \\ 83 | \bottomrule 84 | \end{tabular}}% 85 | \label{tab:2}% 86 | \end{table*}% -------------------------------------------------------------------------------- /资源/参考文献/references.txt: -------------------------------------------------------------------------------- 1 | [1]Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444, 2015. 2 | [2]I. Goodfellow, Y. Bengio, and A. Courville, Deep learning. MIT press, 2016. 3 | [3]A. Voulodimos, N. Doulamis, A. Doulamis, and E. Protopapadakis, "Deep learning for computer vision: A brief review," Computational Intelligence and Neuroscience, 2018. 4 | [4]C. Dong, C. C. Loy, K. He, and X. Tang, "Image super-resolution using deep convolutional networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 2, pp. 295-307, 2015. 5 | [5]Z. Wang, J. Chen, and S. C. Hoi, "Deep learning for image super- resolution: A survey," IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020. 6 | [6]A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classifica- tion with deep convolutional neural networks," Advances in Neural Information Processing Systems, vol. 25, pp. 1097-1105, 2012. 7 | [7]S. Ren, K. He, R. Girshick, and J. Sun, "Faster r-cnn: towards real-time object detection with region proposal networks," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149, 2016. 8 | [8]E. Shelhamer, J. Long, and T. Darrell, "Fully convolutional networks for semantic segmentation." IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 4, pp. 640-651, 2016. 9 | [9]Y. Bengio, Y. LeCun, and G. Hinton, "Deep learning for ai," Communi- cations of the ACM, vol. 64, no. 7, pp. 58-65, 2021. 10 | [10]K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Computer Vision and Pattern Recognition, 2016. 11 | [11]C. Szegedy, A. Toshev, and D. Erhan, "Deep neural networks for object detection," 2013. 12 | [12]R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," in Computer Vision and Pattern Recognition, 2014, pp. 580-587. 13 | [13]B. Kang, Y. Li, S. Xie, Z. Yuan, and J. Feng, "Exploring balanced feature spaces for representation learning," in International Conference on Learning Representations, 2021. 14 | [14]A. K. Menon, S. Jayasumana, A. S. Rawat, H. Jain, A. Veit, and S. Kumar, "Long-tail learning via logit adjustment," in International Conference on Learning Representations, 2021. 15 | [15]Z. Liu, Z. Miao, X. Zhan, J. Wang, B. Gong, and S. X. Yu, "Large- scale long-tailed recognition in an open world," in Computer Vision and Pattern Recognition, 2019, pp. 2537-2546. 16 | [16]Y. Cui, M. Jia, T.-Y. Lin, Y. Song, and S. Belongie, "Class-balanced loss based on effective number of samples," in Computer Vision and Pattern Recognition, 2019, pp. 9268-9277. 17 | [17]X. Wang, L. Lian, Z. Miao, Z. Liu, and S. X. Yu, "Long-tailed recog- nition by routing diverse distribution-aware experts," in International Conference on Learning Representations, 2021. 18 | [18]K. Cao, C. Wei, A. Gaidon, N. Arechiga, and T. Ma, "Learning imbalanced datasets with label-distribution-aware margin loss," in Advances in Neural Information Processing Systems, 2019. 19 | [19]J. Tan, C. Wang, B. Li, Q. Li, W. Ouyang, C. Yin, and J. Yan, "Equalization loss for long-tailed object recognition," in Computer Vision and Pattern Recognition, 2020, pp. 11 662-11 671. 20 | [20]V. Vapnik, "Principles of risk minimization for learning theory," in Advances in Neural Information Processing Systems, 1992, pp. 831-838. 21 | [21]X. Zhang, Z. Fang, Y. Wen, Z. Li, and Y. Qiao, "Range loss for deep face recognition with long-tailed training data," in International Conference on Computer Vision, 2017, pp. 5409-5418. 22 | [22]D. Cao, X. Zhu, X. Huang, J. Guo, and Z. Lei, "Domain balancing: Face recognition on long-tailed domains," in Computer Vision and Pattern Recognition, 2020, pp. 5671-5679. 23 | [23]G. Van Horn, O. Mac Aodha, Y. Song, Y. Cui, C. Sun, A. Shepard, H. Adam, P. Perona, and S. Belongie, "The inaturalist species classifica- tion and detection dataset," in Computer Vision and Pattern Recognition, 2018, pp. 8769-8778. 24 | [24]Z. Miao, Z. Liu, K. M. Gaynor, M. S. Palmer, S. X. Yu, and W. M. Getz, "Iterative human and automated identification of wildlife images," arXiv:2105.02320, 2021. 25 | [25]L. Ju, X. Wang, L. Wang, T. Liu, X. Zhao, T. Drummond, D. Mahapatra, and Z. Ge, "Relational subsets knowledge distillation for long-tailed retinal diseases recognition," arXiv:2104.11057, 2021. 26 | [26]R. He, J. Yang, and X. Qi, "Re-distributing biased pseudo labels for semi-supervised semantic segmentation: A baseline investigation," in International Conference on Computer Vision, 2021. 27 | [27]W. Yu, T. Yang, and C. Chen, "Towards resolving the challenge of long-tail distribution in uav images for object detection," in IEEE Winter Conference on Applications of Computer Vision, 2021, pp. 3258-3267. 28 | [28]M. A. Jamal, M. Brown, M.-H. Yang, L. Wang, and B. Gong, "Rethinking class-balanced methods for long-tailed visual recognition from a domain adaptation perspective," in Computer Vision and Pattern Recognition, 2020, pp. 7610-7619. 29 | [29]S. Zhang, Z. Li, S. Yan, X. He, and J. Sun, "Distribution alignment: A unified framework for long-tail visual recognition," in Computer Vision and Pattern Recognition, 2021, pp. 2361-2370. 30 | [30]Y. Zhang, B. Hooi, L. Hong, and J. Feng, "Test-agnostic long-tailed recog- nition by test-time aggregating diverse experts with self-supervision," arXiv:2107.09249, 2021. 31 | [31]Y. Hong, S. Han, K. Choi, S. Seo, B. Kim, and B. Chang, "Disentangling label distribution for long-tailed visual recognition," in Computer Vision and Pattern Recognition, 2021. 32 | [32]B. Kang, S. Xie, M. Rohrbach, Z. Yan, A. Gordo, J. Feng, and Y. Kalantidis, "Decoupling representation and classifier for long-tailed recognition," in International Conference on Learning Representations, 2020. 33 | [33]C. Feng, Y. Zhong, and W. Huang, "Exploring classification equilibrium in long-tailed object detection," in International Conference on Computer Vision, 2021. 34 | [34]T. Wang, Y. Li, B. Kang, J. Li, J. Liew, S. Tang, S. Hoi, and J. Feng, "The devil is in classification: A simple framework for long-tail instance segmentation," in European Conference on Computer Vision, 2020. 35 | [35]Z. Weng, M. G. Ogut, S. Limonchik, and S. Yeung, "Unsupervised discovery of the long-tail in instance segmentation using hierarchical self-supervision," in Computer Vision and Pattern Recognition, 2021. 36 | [36]A. Gupta, P. Dollar, and R. Girshick, "Lvis: A dataset for large vocabulary instance segmentation," in Computer Vision and Pattern Recognition, 2019, pp. 5356-5364. 37 | [37]T. Wu, Q. Huang, Z. Liu, Y. Wang, and D. Lin, "Distribution-balanced loss for multi-label classification in long-tailed datasets," in European Conference on Computer Vision, 2020, pp. 162-178. 38 | [38]X. Zhang, Z. Wu, Z. Weng, H. Fu, J. Chen, Y.-G. Jiang, and L. Davis, "Videolt: Large-scale long-tailed video recognition," in International Conference on Computer Vision, 2021. 39 | [39]J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, "Imagenet: A large-scale hierarchical image database," in Computer Vision and Pattern Recognition, 2009, pp. 248-255. 40 | [40]A. Krizhevsky, G. Hinton et al., "Learning multiple layers of features from tiny images," 2009. 41 | [41]B. Zhou, A. Lapedriza, J. Xiao, A. Torralba, and A. Oliva, "Learning deep features for scene recognition using places database," Advances in Neural Information Processing Systems, vol. 27, pp. 487-495, 2014. 42 | [42]M. Everingham, S. A. Eslami, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman, "The pascal visual object classes challenge: A retrospective," International Journal of Computer Vision, vol. 111, no. 1, pp. 98-136, 2015. 43 | [43]T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, "Microsoft coco: Common objects in context," in European Conference on Computer Vision, 2014. 44 | [44]H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese, "Generalized intersection over union: A metric and a loss for bounding box regression," in Computer Vision and Pattern Recognition, 2019. 45 | [45]S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He, "Aggregated residual transformations for deep neural networks," in Computer Vision and Pattern Recognition, 2017, pp. 1492-1500. 46 | [46]K. He, G. Gkioxari, P. Dollar, and R. Girshick, "Mask r-cnn," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 2, pp. 386-397, 2020. 47 | [47]T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, "Feature pyramid networks for object detection," in Computer Vision and Pattern Recognition, 2017, pp. 2117-2125. 48 | [48]B. Zhou, Q. Cui, X.-S. Wei, and Z.-M. Chen, "Bbn: Bilateral-branch network with cumulative learning for long-tailed visual recognition," in Computer Vision and Pattern Recognition, 2020, pp. 9719-9728. 49 | [49]H. He and E. A. Garcia, "Learning from imbalanced data," IEEE Transactions on Knowledge and Data Engineering, vol. 21, no. 9, pp. 1263-1284, 2009. 50 | [50]J. Snell, K. Swersky, and R. Zemel, "Prototypical networks for few-shot learning," Advances in Neural Information Processing Systems, 2017. 51 | [51]F. Sung, Y. Yang, L. Zhang, T. Xiang, P. H. Torr, and T. M. Hospedales, "Learning to compare: Relation network for few-shot learning," in Computer Vision and Pattern Recognition, 2018, pp. 1199-1208. 52 | [52]Q. Sun, Y. Liu, T.-S. Chua, and B. Schiele, "Meta-transfer learning for few-shot learning," in Computer Vision and Pattern Recognition, 2019. 53 | [53]Y. Wang, Q. Yao, J. T. Kwok, and L. M. Ni, "Generalizing from a few examples: A survey on few-shot learning," ACM Computing Surveys, vol. 53, no. 3, pp. 1-34, 2020. 54 | [54]D. Krueger, E. Caballero et al., "Out-of-distribution generalization via risk extrapolation," in International Conference on Machine Learning, 2021, pp. 5815-5826. 55 | [55]Z. Shen, J. Liu, Y. He, X. Zhang, R. Xu, H. Yu, and P. Cui, "Towards out-of-distribution generalization: A survey," arXiv:2108.13624, 2021. 56 | [56]S. J. Pan, I. W. Tsang, J. T. Kwok, and Q. Yang, "Domain adaptation via transfer component analysis," IEEE Transactions on Neural Networks, vol. 22, no. 2, pp. 199-210, 2010. 57 | [57]E. Tzeng, J. Hoffman, K. Saenko, and T. Darrell, "Adversarial discrimi- native domain adaptation," in Computer Vision and Pattern Recognition, 2017, pp. 7167-7176. 58 | [58]Y. Zhang, H. Chen, Y. Wei, P. Zhao, J. Cao, X. Fan, X. Lou, H. Liu, J. Hou, X. Han et al., "From whole slide imaging to microscopy: Deep microscopy adaptation network for histopathology cancer image classification," in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2019, pp. 360-368. 59 | [59]Y. Zhang, Y. Wei et al., "Collaborative unsupervised domain adaptation for medical image diagnosis," IEEE Transactions on Image Processing, 2020. 60 | [60]Z. Qiu, Y. Zhang, H. Lin, S. Niu, Y. Liu, Q. Du, and M. Tan, "Source-free domain adaptation via avatar prototype generation and adaptation," in International Joint Conference on Artificial Intelligence, 2021. 61 | [61]H. Wu, H. Zhu, Y. Yan, J. Wu, Y. Zhang, and M. K. Ng, "Heterogeneous domain adaptation by information capturing and distribution matching," IEEE Transactions on Image Processing, vol. 30, pp. 6364-6376, 2021. 62 | [62]D. Li, Y. Yang, Y.-Z. Song, and T. M. Hospedales, "Deeper, broader and artier domain generalization," in International Conference on Computer Vision, 2017, pp. 5542-5550. 63 | [63]H. Li, S. J. Pan, S. Wang, and A. C. Kot, "Domain generalization with adversarial feature learning," in Computer Vision and Pattern Recognition, 2018, pp. 5400-5409. 64 | [64]L. Neal, M. Olson, X. Fern, W.-K. Wong, and F. Li, "Open set learning with counterfactual images," in European Conference on Computer Vision, 2018, pp. 613-628. 65 | [65]Y. Fu, X. Wang, H. Dong, Y.-G. Jiang, M. Wang, X. Xue, and L. Sigal, "Vocabulary-informed zero-shot and open-set learning," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 12, pp. 3136-3152, 2019. 66 | [66]C. Huang, Y. Li, C. C. Loy, and X. Tang, "Learning deep represen- tation for imbalanced classification," in Computer Vision and Pattern Recognition, 2016. 67 | [67]W. Ouyang, X. Wang, C. Zhang, and X. Yang, "Factors in finetuning deep model for object detection with long-tail distribution," in Computer Vision and Pattern Recognition, 2016, pp. 864-873. 68 | [68]T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, "Focal loss for dense object detection," in International Conference on Computer Vision, 2017, pp. 2980-2988. 69 | [69]Q. Dong, S. Gong, and X. Zhu, "Class rectification hard mining for imbalanced deep learning," in International Conference on Computer Vision, 2017, pp. 1851-1860. 70 | [70]Y.-X. Wang, D. Ramanan, and M. Hebert, "Learning to model the tail," in Advances in Neural Information Processing Systems, 2017. 71 | [71]Y. Cui, Y. Song, C. Sun, A. Howard, and S. Belongie, "Large scale fine-grained categorization and domain-specific transfer learning," in Computer Vision and Pattern Recognition, 2018, pp. 4109-4118. 72 | [72]S. Khan, M. Hayat, S. W. Zamir, J. Shen, and L. Shao, "Striking the right balance with uncertainty," in Computer Vision and Pattern Recognition, 2019, pp. 103-112. 73 | [73]X. Yin, X. Yu, K. Sohn, X. Liu, and M. Chandraker, "Feature transfer learning for face recognition with under-represented data," in Computer Vision and Pattern Recognition, 2019, pp. 5704-5713. 74 | [74]Y. Zhong, W. Deng, M. Wang, J. Hu, J. Peng, X. Tao, and Y. Huang, "Unequal-training for deep face recognition with long-tailed noisy data," in Computer Vision and Pattern Recognition, 2019, pp. 7812-7821. 75 | [75]Y. Wang, W. Gan, J. Yang, W. Wu, and J. Yan, "Dynamic curriculum learning for imbalanced data classification," in International Conference on Computer Vision, 2019, pp. 5017-5026. 76 | [76]J. Shu, Q. Xie, L. Yi, Q. Zhao, S. Zhou, Z. Xu, and D. Meng, "Meta-weight-net: Learning an explicit mapping for sample weighting," Advances in Neural Information Processing Systems, 2019. 77 | [77]X. Hu, Y. Jiang, K. Tang, J. Chen, C. Miao, and H. Zhang, "Learning to segment the tail," in Computer Vision and Pattern Recognition, 2020. 78 | [78]Y. Li, T. Wang, B. Kang, S. Tang, C. Wang, J. Li, and J. Feng, "Overcoming classifier imbalance for long-tail object detection with balanced group softmax," in Computer Vision and Pattern Recognition, 2020, pp. 10 991-11 000. 79 | [79]J. Kim, J. Jeong, and J. Shin, "M2m: Imbalanced classification via major- to-minor translation," in Computer Vision and Pattern Recognition, 2020. 80 | [80]J. Liu, Y. Sun, C. Han, Z. Dou, and W. Li, "Deep representation learning on long-tailed data: A learnable embedding augmentation perspective," in Computer Vision and Pattern Recognition, 2020. 81 | [81]L. Zhu and Y. Yang, "Inflated episodic memory with region self-attention for long-tailed visual recognition," in Computer Vision and Pattern Recognition, 2020, pp. 4344-4353. 82 | [82]C. D. Kim, J. Jeong, and G. Kim, "Imbalanced continual learning with partitioning reservoir sampling," in European Conference on Computer Vision, 2020, pp. 411-428. 83 | [83]P. Chu, X. Bian, S. Liu, and H. Ling, "Feature space augmentation for long-tailed data," in European Conference on Computer Vision, 2020. 84 | [84]L. Xiang, G. Ding, and J. Han, "Learning from multiple experts: Self- paced knowledge distillation for long-tailed classification," in European Conference on Computer Vision, 2020, pp. 247-263. 85 | [85]T.-Y. Wu, P. Morgado, P. Wang, C.-H. Ho, and N. Vasconcelos, "Solving long-tailed recognition with deep realistic taxonomic classifier," in European Conference on Computer Vision, 2020, pp. 171-189. 86 | [86]R. Jiawei, C. Yu, X. Ma, H. Zhao, S. Yi et al., "Balanced meta-softmax for long-tailed visual recognition," in Advances in Neural Information Processing Systems, 2020. 87 | [87]J. Tian, Y.-C. Liu, N. Glaser, Y.-C. Hsu, and Z. Kira, "Posterior re- calibration for imbalanced datasets," in Advances in Neural Information Processing Systems, 2020. 88 | [88]K. Tang, J. Huang, and H. Zhang, "Long-tailed classification by keeping the good and removing the bad momentum causal effect," Advances in Neural Information Processing Systems, vol. 33, 2020. 89 | [89]Y. Yang and Z. Xu, "Rethinking the value of labels for improving class- imbalanced learning," in Advances in Neural Information Processing Systems, 2020. 90 | [90]H. Guo and S. Wang, "Long-tailed multi-label visual recognition by collaborative training on uniform and re-balanced samplings," in Computer Vision and Pattern Recognition, 2021, pp. 15 089-15 098. 91 | [91]J. Tan, X. Lu, G. Zhang, C. Yin, and Q. Li, "Equalization loss v2: A new gradient balance approach for long-tailed object detection," in Computer Vision and Pattern Recognition, 2021, pp. 1685-1694. 92 | [92]J. Wang, W. Zhang, Y. Zang, Y. Cao, J. Pang, T. Gong, K. Chen, Z. Liu, C. C. Loy, and D. Lin, "Seesaw loss for long-tailed instance segmentation," in Computer Vision and Pattern Recognition, 2021. 93 | [93]T. Wang, Y. Zhu, C. Zhao, W. Zeng, J. Wang, and M. Tang, "Adaptive class suppression loss for long-tail object detection," in Computer Vision and Pattern Recognition, 2021, pp. 3103-3112. 94 | [94]Z. Deng, H. Liu, Y. Wang, C. Wang, Z. Yu, and X. Sun, "Pml: Progressive margin loss for long-tailed age classification," in Computer Vision and Pattern Recognition, 2021, pp. 10 503-10 512. 95 | [95]T. Wu, Z. Liu, Q. Huang, Y. Wang, and D. Lin, "Adversarial robust- ness under long-tailed distribution," in Computer Vision and Pattern Recognition, 2021, pp. 8659-8668. 96 | [96]Z. Zhong, J. Cui, S. Liu, and J. Jia, "Improving calibration for long-tailed recognition," in Computer Vision and Pattern Recognition, 2021. 97 | [97]C. Wei, K. Sohn, C. Mellina, A. Yuille, and F. Yang, "Crest: A class- rebalancing self-training framework for imbalanced semi-supervised learning," in Computer Vision and Pattern Recognition, 2021. 98 | [98]S. Changpinyo, P. Sharma, N. Ding, and R. Soricut, "Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts," in Computer Vision and Pattern Recognition, 2021. 99 | [99]J. Wang, T. Lukasiewicz, X. Hu, J. Cai, and Z. Xu, "Rsg: A simple but effective module for learning imbalanced datasets," in Computer Vision and Pattern Recognition, 2021, pp. 3784-3793. 100 | [100]S. Li, K. Gong, C. H. Liu, Y. Wang, F. Qiao, and X. Cheng, "Metasaug: Meta semantic augmentation for long-tailed visual recognition," in Computer Vision and Pattern Recognition, 2021, pp. 5212-5221. 101 | [101]P. Wang, K. Han, X.-S. Wei, L. Zhang, and L. Wang, "Contrastive learning based hybrid networks for long-tailed image classification," in Computer Vision and Pattern Recognition, 2021, pp. 943-952. 102 | [102]B. Liu, H. Li, H. Kang, G. Hua, and N. Vasconcelos, "Gistnet: a geometric structure transfer network for long-tailed recognition," in International Conference on Computer Vision, 2021. 103 | [103]Y. Zang, C. Huang, and C. C. Loy, "Fasa: Feature augmentation and sampling adaptation for long-tailed instance segmentation," in International Conference on Computer Vision, 2021. 104 | [104]J. Cai, Y. Wang, and J.-N. Hwang, "Ace: Ally complementary experts for solving long-tailed recognition in one-shot," in International Conference on Computer Vision, 2021. 105 | [105]S. Park, J. Lim, Y. Jeon, and J. Y. Choi, "Influence-balanced loss for imbalanced visual classification," in International Conference on Computer Vision, 2021. 106 | [106]T. Li, L. Wang, and G. Wu, "Self supervision to distillation for long- tailed visual recognition," in International Conference on Computer Vision, 2021. 107 | [107]Y.-Y. He, J. Wu, and X.-S. Wei, "Distilling virtual examples for long- tailed recognition," in International Conference on Computer Vision, 2021. 108 | [108]C. Zhang, T.-Y. Pan, Y. Li, H. Hu, D. Xuan, S. Changpinyo, B. Gong, and W.-L. Chao, "Mosaicos: A simple and effective use of object-centric images for long-tailed object detection," in International Conference on Computer Vision, 2021. 109 | [109]J. Cui, Z. Zhong, S. Liu, B. Yu, and J. Jia, "Parametric contrastive learning," in International Conference on Computer Vision, 2021. 110 | [110]D. Samuel and G. Chechik, "Distributional robustness loss for long-tail learning," in International Conference on Computer Vision, 2021. 111 | [111]A. Desai, T.-Y. Wu, S. Tripathi, and N. Vasconcelos, "Learning of visual relations: The devil is in the tails," in International Conference on Computer Vision, 2021. 112 | [112]N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "Smote: synthetic minority over-sampling technique," Journal of artificial intelligence research, vol. 16, pp. 321-357, 2002. 113 | [113]A. Estabrooks, T. Jo, and N. Japkowicz, "A multiple resampling method for learning from imbalanced data sets," Computational Intelligence, vol. 20, no. 1, pp. 18-36, 2004. 114 | [114]H. Han, W.-Y. Wang, and B.-H. Mao, "Borderline-smote: a new over- sampling method in imbalanced data sets learning," in International Conference on Intelligent Computing, 2005, pp. 878-887. 115 | [115]X.-Y. Liu, J. Wu, and Z.-H. Zhou, "Exploratory undersampling for class-imbalance learning," IEEE Transactions on Systems, Man, and Cybernetics, vol. 39, no. 2, pp. 539-550, 2008. 116 | [116]Z. Zhang and T. Pfister, "Learning fast sample re-weighting without reward data," in International Conference on Computer Vision, 2021. 117 | [117]D. Mahajan, R. Girshick, V. Ramanathan, K. He, M. Paluri, Y. Li, A. Bharambe, and L. Van Der Maaten, "Exploring the limits of weakly supervised pretraining," in European conference on computer vision, 2018, pp. 181-196. 118 | [118]A. Hermans, L. Beyer, and B. Leibe, "In defense of the triplet loss for person re-identification," arXiv:1703.07737, 2017. 119 | [119]C. Elkan, "The foundations of cost-sensitive learning," in International Joint Conference on Artificial Intelligence, 2001. 120 | [120]Z.-H. Zhou and X.-Y. Liu, "Training cost-sensitive neural networks with methods addressing the class imbalance problem," IEEE Transactions on Knowledge and Data Engineering, vol. 18, no. 1, pp. 63-77, 2005. 121 | [121]Y. Sun, M. S. Kamel, A. K. Wong, and Y. Wang, "Cost-sensitive boosting for classification of imbalanced data," Pattern Recognition, vol. 40, no. 12, pp. 3358-3378, 2007. 122 | [122]P. Zhao, Y. Zhang, M. Wu, S. C. Hoi, M. Tan, and J. Huang, "Adaptive cost-sensitive online classification," IEEE Transactions on Knowledge and Data Engineering, vol. 31, no. 2, pp. 214-228, 2018. 123 | [123]Y. Zhang, P. Zhao, J. Cao, W. Ma, J. Huang, Q. Wu, and M. Tan, "Online adaptive asymmetric active learning for budgeted imbalanced data," in SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018, pp. 2768-2777. 124 | [124]Y. Zhang, P. Zhao, S. Niu, Q. Wu, J. Cao, J. Huang, and M. Tan, "Online adaptive asymmetric active learning with limited budgets," IEEE Transactions on Knowledge and Data Engineering, 2019. 125 | [125]H.-J. Ye, H.-Y. Chen, D.-C. Zhan, and W.-L. Chao, "Identifying and compensating for feature deviation in imbalanced deep learning," arXiv:2001.01385, 2020. 126 | [126]T.-I. Hsieh, E. Robb, H.-T. Chen, and J.-B. Huang, "Droploss for long- tail instance segmentation," in AAAI Conference on Artificial Intelligence, vol. 35, no. 2, 2021, pp. 1549-1557. 127 | [127]F. Wang, J. Cheng, W. Liu, and H. Liu, "Additive margin softmax for face verification," IEEE Signal Processing Letters, vol. 25, no. 7, pp. 926-930, 2018. 128 | [128]V. Koltchinskii and D. Panchenko, "Empirical margin distributions and bounding the generalization error of combined classifiers," The Annals of Statistics, vol. 30, no. 1, pp. 1-50, 2002. 129 | [129]F. Provost, "Machine learning from imbalanced data sets 101," in AAAI Workshop on Imbalanced Data Sets, vol. 68, no. 2000, 2000, pp. 1-3. 130 | [130]S. J. Pan and Q. Yang, "A survey on transfer learning," IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345-1359, 2009. 131 | [131]C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, "A survey on deep transfer learning," in International Conference on Artificial Neural Networks, 2018, pp. 270-279. 132 | [132]B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, "Learning deep features for discriminative localization," in Computer Vision and Pattern Recognition, 2016, pp. 2921-2929. 133 | [133]D. Erhan, A. Courville, Y. Bengio, and P. Vincent, "Why does unsuper- vised pre-training help deep learning?" in International Conference on Artificial Intelligence and Statistics, 2010, pp. 201-208. 134 | [134]K. He, R. Girshick, and P. Dollár, "Rethinking imagenet pre-training," in International Conference on Computer Vision, 2019, pp. 4918-4927. 135 | [135]D. Hendrycks, K. Lee, and M. Mazeika, "Using pre-training can improve model robustness and uncertainty," in International Conference on Machine Learning, 2019, pp. 2712-2721. 136 | [136]B. Zoph, G. Ghiasi, T.-Y. Lin, Y. Cui, H. Liu, E. D. Cubuk, and Q. Le, "Rethinking pre-training and self-training," Advances in Neural Information Processing Systems. 137 | [137]Y. Zhang, B. Hooi, D. Hu, J. Liang, and J. Feng, "Unleashing the power of contrastive self-supervised visual models via contrast-regularized fine-tuning," in Advances in Neural Information Processing Systems, 2021. 138 | [138]K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick, "Momentum contrast for unsupervised visual representation learning," in Computer Vision and Pattern Recognition, 2020. 139 | [139]S. Gidaris, P. Singh, and N. Komodakis, "Unsupervised representation learning by predicting image rotations," in International Conference on Learning Representations, 2018. 140 | [140]S. Karthik, J. Revaud, and C. Boris, "Learning from long-tailed data with noisy labels," arXiv:2108.11096, 2021. 141 | [141]G. Hinton, O. Vinyals, and J. Dean, "Distilling the knowledge in a neural network," arXiv:1503.02531, 2015. 142 | [142]J. Gou, B. Yu, S. J. Maybank, and D. Tao, "Knowledge distillation: A survey," International Journal of Computer Vision, vol. 129, no. 6, pp. 1789-1819, 2021. 143 | [143]X. J. Zhu, "Semi-supervised learning literature survey," 2005. 144 | [144]C. Rosenberg, M. Hebert, and H. Schneiderman, "Semi-supervised self- training of object detection models," 2005. 145 | [145]T. Wei, J.-X. Shi, W.-W. Tu, and Y.-F. Li, "Robust long-tailed learning under label noise," arXiv:2108.11569, 2021. 146 | [146]L. Perez and J. Wang, "The effectiveness of data augmentation in image classification using deep learning," arXiv:1712.04621, 2017. 147 | [147]C. Shorten and T. M. Khoshgoftaar, "A survey on image data augmen- tation for deep learning," Journal of Big Data, vol. 6, no. 1, pp. 1-48, 2019. 148 | [148]H.-P. Chou, S.-C. Chang, J.-Y. Pan, W. Wei, and D.-C. Juan, "Remix: Rebalanced mixup," in European Conference on Computer Vision Workshop, 2020, pp. 95-110. 149 | [149]Y. Wang, X. Pan, S. Song, H. Zhang, G. Huang, and C. Wu, "Implicit semantic data augmentation for deep networks," in Advances in Neural Information Processing Systems, vol. 32, 2019, pp. 12 635-12 644. 150 | [150]J. Goh and M. Sim, "Distributionally robust optimization and its tractable approximations," Operations Research, vol. 58, no. 4-part-1, pp. 902- 917, 2010. 151 | [151]T. Cover and P. Hart, "Nearest neighbor pattern classification," IEEE transactions on information theory, vol. 13, no. 1, pp. 21-27, 1967. 152 | [152]J. Cui, S. Liu, Z. Tian, Z. Zhong, and J. Jia, "Reslt: Residual learning for long-tailed recognition," arXiv:2101.10633, 2021. 153 | [153]E. D. Cubuk, B. Zoph, J. Shlens, and Q. Le, "Randaugment: Practical automated data augmentation with a reduced search space," Advances in Neural Information Processing Systems, vol. 33, 2020. 154 | [154]S. Yun, D. Han, S. J. Oh, S. Chun, J. Choe, and Y. Yoo, "Cutmix: Regularization strategy to train strong classifiers with localizable features," in International Conference on Computer Vision, 2019. 155 | [155]M. R. Keaton, R. J. Zaveri, M. Kovur, C. Henderson, D. A. Adjeroh, and G. Doretto, "Fine-grained visual classification of plant species in the wild: Object detection as a reinforced means of attention," arXiv:2106.02141, 2021. 156 | [156]X. Jia, H. Yan, Y. Wu, X. Wei, X. Cao, and Y. Zhang, "An effective and robust detector for logo detection," arXiv:2108.00422, 2021. 157 | [157]Z. Zhang, S. Yu, S. Yang, Y. Zhou, and B. Zhao, "Rail-5k: a real-world dataset for rail surface defects detection," arXiv:2106.14366, 2021. 158 | [158]A. Galdran, G. Carneiro, and M. A. G. Ballester, "Balanced-mixup for highly imbalanced medical image classification," in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2021. 159 | [159]T. Weyand, A. Araujo, B. Cao, and J. Sim, "Google landmarks dataset v2-a large-scale benchmark for instance-level recognition and retrieval," in Computer Vision and Pattern Recognition, 2020, pp. 2575-2584. 160 | [160]J. Wu, L. Song, T. Wang, Q. Zhang, and J. Yuan, "Forest r-cnn: Large- vocabulary long-tailed object detection and instance segmentation," in ACM International Conference on Multimedia, 2020, pp. 1570-1578. 161 | [161]J. Mao, M. Niu, C. Jiang, H. Liang, X. Liang, Y. Li, C. Ye, W. Zhang, Z. Li, J. Yu et al., "One million scenes for autonomous driving: Once dataset," in NeurIPS 2021 Datasets and Benchmarks Track, 2021. 162 | [162]Y. Zhang, Z. Zhou, P. David, X. Yue, Z. Xi, B. Gong, and H. Foroosh, "Polarnet: An improved grid representation for online lidar point clouds semantic segmentation," in Computer Vision and Pattern Recognition, 2020, pp. 9601-9610. 163 | [163]X. Chen, C. Zhang, G. Lin, and J. Han, "Compositional prototype network with multi-view comparision for few-shot point cloud semantic segmentation," arXiv:2012.14255, 2020. 164 | [164]N. Dhingra, F. Ritter, and A. Kunz, "Bgt-net: Bidirectional gru trans- former network for scene graph generation," in Computer Vision and Pattern Recognition, 2021, pp. 2150-2159. 165 | [165]J. Chen, A. Agarwal, S. Abdelkarim, D. Zhu, and M. Elhoseiny, "Reltransformer: Balancing the visual relationship detection from local context, scene and memory," arXiv:2104.11934, 2021. 166 | [166]Z. Li, E. Stengel-Eskin, Y. Zhang, C. Xie, Q. Tran, B. Van Durme, and A. Yuille, "Calibrating concepts and operations: Towards symbolic reasoning on real images," in International Conference on Computer Vision, 2021. 167 | [167]M. Luo, F. Chen, D. Hu, Y. Zhang, J. Liang, and J. Feng, "No fear of heterogeneity: Classifier calibration for federated learning with non-iid data," in Advances in Neural Information Processing Systems, 2021. 168 | [168]S. Niu, J. Wu, G. Xu, Y. Zhang, Y. Guo, P. Zhao, P. Wang, and M. Tan, "Adaxpert: Adapting neural architecture for growing data," in International Conference on Machine Learning, 2021, pp. 8184-8194. 169 | [169]Y. Zhang, S. Niu, Z. Qiu, Y. Wei, P. Zhao, J. Yao, J. Huang, Q. Wu, and M. Tan, "Covid-da: Deep domain adaptation from typical pneumonia to covid-19," arXiv:2005.01577, 2020. 170 | [170]X. Peng, Q. Bai, X. Xia, Z. Huang, K. Saenko, and B. Wang, "Moment matching for multi-source domain adaptation," in International Conference on Computer Vision, 2019, pp. 1406-1415. 171 | [171]K. Cao, Y. Chen, J. Lu, N. Arechiga, A. Gaidon, and T. Ma, "Het- eroskedastic and imbalanced deep learning with adaptive regularization," in International Conference on Learning Representations, 2021. 172 | [172]Y. Yang, K. Zha, Y.-C. Chen, H. Wang, and D. Katabi, "Delving into deep imbalanced regression," in International Conference on Machine Learning, 2021. -------------------------------------------------------------------------------- /资源/参考文献/references.bib: -------------------------------------------------------------------------------- 1 | @article{LeCun_2015, 2 | doi = {10.1038/nature14539}, 3 | url = {https://doi.org/10.1038%2Fnature14539}, 4 | year = 2015, 5 | month = {may}, 6 | publisher = {Springer Science and Business Media {LLC}}, 7 | volume = {521}, 8 | number = {7553}, 9 | pages = {436--444}, 10 | author = {Yann LeCun and Yoshua Bengio and Geoffrey Hinton}, 11 | title = {Deep learning}, 12 | journal = {Nature} 13 | } 14 | @book{goodfellow2016deep, 15 | title={Deep learning}, 16 | author={Goodfellow, Ian and Bengio, Yoshua and Courville, Aaron}, 17 | year={2016}, 18 | publisher={MIT press} 19 | } 20 | @article{Voulodimos_2018, 21 | doi = {10.1155/2018/7068349}, 22 | url = {https://doi.org/10.1155%2F2018%2F7068349}, 23 | year = 2018, 24 | publisher = {Hindawi Limited}, 25 | volume = {2018}, 26 | pages = {1--13}, 27 | author = {Athanasios Voulodimos and Nikolaos Doulamis and Anastasios Doulamis and Eftychios Protopapadakis}, 28 | title = {Deep Learning for Computer Vision: A Brief Review}, 29 | journal = {Computational Intelligence and Neuroscience} 30 | } 31 | @article{Dong_2016, 32 | doi = {10.1109/tpami.2015.2439281}, 33 | url = {https://doi.org/10.1109%2Ftpami.2015.2439281}, 34 | year = 2016, 35 | month = {feb}, 36 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 37 | volume = {38}, 38 | number = {2}, 39 | pages = {295--307}, 40 | author = {Chao Dong and Chen Change Loy and Kaiming He and Xiaoou Tang}, 41 | title = {Image Super-Resolution Using Deep Convolutional Networks}, 42 | journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence} 43 | } 44 | @article{Wang_2021_deep, 45 | doi = {10.1109/tpami.2020.2982166}, 46 | url = {https://doi.org/10.1109%2Ftpami.2020.2982166}, 47 | year = 2021, 48 | month = {oct}, 49 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 50 | volume = {43}, 51 | number = {10}, 52 | pages = {3365--3387}, 53 | author = {Zhihao Wang and Jian Chen and Steven C. H. Hoi}, 54 | title = {Deep Learning for Image Super-Resolution: A Survey}, 55 | journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence} 56 | } 57 | @article{Krizhevsky_2017, 58 | doi = {10.1145/3065386}, 59 | url = {https://doi.org/10.1145%2F3065386}, 60 | year = 2017, 61 | month = {may}, 62 | publisher = {Association for Computing Machinery ({ACM})}, 63 | volume = {60}, 64 | number = {6}, 65 | pages = {84--90}, 66 | author = {Alex Krizhevsky and Ilya Sutskever and Geoffrey E. Hinton}, 67 | title = {{ImageNet} classification with deep convolutional neural networks}, 68 | journal = {Communications of the {ACM}} 69 | } 70 | @article{Ren_2017, 71 | doi = {10.1109/tpami.2016.2577031}, 72 | url = {https://doi.org/10.1109%2Ftpami.2016.2577031}, 73 | year = 2017, 74 | month = {jun}, 75 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 76 | volume = {39}, 77 | number = {6}, 78 | pages = {1137--1149}, 79 | author = {Shaoqing Ren and Kaiming He and Ross Girshick and Jian Sun}, 80 | title = {Faster R-{CNN}: Towards Real-Time Object Detection with Region Proposal Networks}, 81 | journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence} 82 | } 83 | @article{Shelhamer_2017, 84 | doi = {10.1109/tpami.2016.2572683}, 85 | url = {https://doi.org/10.1109%2Ftpami.2016.2572683}, 86 | year = 2017, 87 | month = {apr}, 88 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 89 | volume = {39}, 90 | number = {4}, 91 | pages = {640--651}, 92 | author = {Evan Shelhamer and Jonathan Long and Trevor Darrell}, 93 | title = {Fully Convolutional Networks for Semantic Segmentation}, 94 | journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence} 95 | } 96 | @article{Bengio_2021, 97 | doi = {10.1145/3448250}, 98 | url = {https://doi.org/10.1145%2F3448250}, 99 | year = 2021, 100 | month = {jul}, 101 | publisher = {Association for Computing Machinery ({ACM})}, 102 | volume = {64}, 103 | number = {7}, 104 | pages = {58--65}, 105 | author = {Yoshua Bengio and Yann Lecun and Geoffrey Hinton}, 106 | title = {Deep learning for {AI}}, 107 | journal = {Communications of the {ACM}} 108 | } 109 | @inproceedings{He_2016, 110 | doi = {10.1109/cvpr.2016.90}, 111 | url = {https://doi.org/10.1109%2Fcvpr.2016.90}, 112 | year = 2016, 113 | month = {jun}, 114 | publisher = {{IEEE}}, 115 | author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun}, 116 | title = {Deep Residual Learning for Image Recognition}, 117 | booktitle = {2016 {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})} 118 | } 119 | @article{szegedy2013deep, 120 | title={Deep neural networks for object detection}, 121 | author={Szegedy, Christian and Toshev, Alexander and Erhan, Dumitru}, 122 | journal={Advances in neural information processing systems}, 123 | volume={26}, 124 | year={2013} 125 | } 126 | @inproceedings{Girshick_2014, 127 | doi = {10.1109/cvpr.2014.81}, 128 | url = {https://doi.org/10.1109%2Fcvpr.2014.81}, 129 | year = 2014, 130 | month = {jun}, 131 | publisher = {{IEEE}}, 132 | author = {Ross Girshick and Jeff Donahue and Trevor Darrell and Jitendra Malik}, 133 | title = {Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation}, 134 | booktitle = {2014 {IEEE} Conference on Computer Vision and Pattern Recognition} 135 | } 136 | @inproceedings{kang2020exploring, 137 | title={Exploring balanced feature spaces for representation learning}, 138 | author={Kang, Bingyi and Li, Yu and Xie, Sa and Yuan, Zehuan and Feng, Jiashi}, 139 | booktitle={International Conference on Learning Representations}, 140 | year={2020} 141 | } 142 | @article{menon2020long, 143 | title={Long-tail learning via logit adjustment}, 144 | author={Menon, Aditya Krishna and Jayasumana, Sadeep and Rawat, Ankit Singh and Jain, Himanshu and Veit, Andreas and Kumar, Sanjiv}, 145 | journal={arXiv preprint arXiv:2007.07314}, 146 | year={2020} 147 | } 148 | @inproceedings{Liu_2019, 149 | doi = {10.1109/cvpr.2019.00264}, 150 | url = {https://doi.org/10.1109%2Fcvpr.2019.00264}, 151 | year = 2019, 152 | month = {jun}, 153 | publisher = {{IEEE}}, 154 | author = {Ziwei Liu and Zhongqi Miao and Xiaohang Zhan and Jiayun Wang and Boqing Gong and Stella X. Yu}, 155 | title = {Large-Scale Long-Tailed Recognition in an Open World}, 156 | booktitle = {2019 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 157 | } 158 | @inproceedings{Cui_2019, 159 | doi = {10.1109/cvpr.2019.00949}, 160 | url = {https://doi.org/10.1109%2Fcvpr.2019.00949}, 161 | year = 2019, 162 | month = {jun}, 163 | publisher = {{IEEE}}, 164 | author = {Yin Cui and Menglin Jia and Tsung-Yi Lin and Yang Song and Serge Belongie}, 165 | title = {Class-Balanced Loss Based on Effective Number of Samples}, 166 | booktitle = {2019 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 167 | } 168 | @article{wang2020long, 169 | title={Long-tailed recognition by routing diverse distribution-aware experts}, 170 | author={Wang, Xudong and Lian, Long and Miao, Zhongqi and Liu, Ziwei and Yu, Stella X}, 171 | journal={arXiv preprint arXiv:2010.01809}, 172 | year={2020} 173 | } 174 | @article{cao2019learning, 175 | title={Learning imbalanced datasets with label-distribution-aware margin loss}, 176 | author={Cao, Kaidi and Wei, Colin and Gaidon, Adrien and Arechiga, Nikos and Ma, Tengyu}, 177 | journal={Advances in neural information processing systems}, 178 | volume={32}, 179 | year={2019} 180 | } 181 | @inproceedings{Tan_2020, 182 | doi = {10.1109/cvpr42600.2020.01168}, 183 | url = {https://doi.org/10.1109%2Fcvpr42600.2020.01168}, 184 | year = 2020, 185 | month = {jun}, 186 | publisher = {{IEEE}}, 187 | author = {Jingru Tan and Changbao Wang and Buyu Li and Quanquan Li and Wanli Ouyang and Changqing Yin and Junjie Yan}, 188 | title = {Equalization Loss for Long-Tailed Object Recognition}, 189 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 190 | } 191 | @article{vapnik1991principles, 192 | title={Principles of risk minimization for learning theory}, 193 | author={Vapnik, Vladimir}, 194 | journal={Advances in neural information processing systems}, 195 | volume={4}, 196 | year={1991} 197 | } 198 | @inproceedings{Zhang_2017, 199 | doi = {10.1109/iccv.2017.578}, 200 | url = {https://doi.org/10.1109%2Ficcv.2017.578}, 201 | year = 2017, 202 | month = {oct}, 203 | publisher = {{IEEE}}, 204 | author = {Xiao Zhang and Zhiyuan Fang and Yandong Wen and Zhifeng Li and Yu Qiao}, 205 | title = {Range Loss for Deep Face Recognition with Long-Tailed Training Data}, 206 | booktitle = {2017 {IEEE} International Conference on Computer Vision ({ICCV})} 207 | } 208 | @inproceedings{Cao_2020, 209 | doi = {10.1109/cvpr42600.2020.00571}, 210 | url = {https://doi.org/10.1109%2Fcvpr42600.2020.00571}, 211 | year = 2020, 212 | month = {jun}, 213 | publisher = {{IEEE}}, 214 | author = {Dong Cao and Xiangyu Zhu and Xingyu Huang and Jianzhu Guo and Zhen Lei}, 215 | title = {Domain Balancing: Face Recognition on Long-Tailed Domains}, 216 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 217 | } 218 | @inproceedings{Van_Horn_2018, 219 | doi = {10.1109/cvpr.2018.00914}, 220 | url = {https://doi.org/10.1109%2Fcvpr.2018.00914}, 221 | year = 2018, 222 | month = {jun}, 223 | publisher = {{IEEE}}, 224 | author = {Grant Van Horn and Oisin Mac Aodha and Yang Song and Yin Cui and Chen Sun and Alex Shepard and Hartwig Adam and Pietro Perona and Serge Belongie}, 225 | title = {The {iNaturalist} Species Classification and Detection Dataset}, 226 | booktitle = {2018 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition} 227 | } 228 | @article{Miao_2021, 229 | doi = {10.1038/s42256-021-00393-0}, 230 | url = {https://doi.org/10.1038%2Fs42256-021-00393-0}, 231 | year = 2021, 232 | month = {oct}, 233 | publisher = {Springer Science and Business Media {LLC}}, 234 | volume = {3}, 235 | number = {10}, 236 | pages = {885--895}, 237 | author = {Zhongqi Miao and Ziwei Liu and Kaitlyn M. Gaynor and Meredith S. Palmer and Stella X. Yu and Wayne M. Getz}, 238 | title = {Iterative human and automated identification of wildlife images}, 239 | journal = {Nature Machine Intelligence} 240 | } 241 | @incollection{Ju_2021, 242 | doi = {10.1007/978-3-030-87237-3_1}, 243 | url = {https://doi.org/10.1007%2F978-3-030-87237-3_1}, 244 | year = 2021, 245 | publisher = {Springer International Publishing}, 246 | pages = {3--12}, 247 | author = {Lie Ju and Xin Wang and Lin Wang and Tongliang Liu and Xin Zhao and Tom Drummond and Dwarikanath Mahapatra and Zongyuan Ge}, 248 | title = {Relational Subsets Knowledge Distillation for Long-Tailed Retinal Diseases Recognition}, 249 | booktitle = {Medical Image Computing and Computer Assisted Intervention {\textendash} {MICCAI} 2021} 250 | } 251 | @inproceedings{He_2021_redis, 252 | doi = {10.1109/iccv48922.2021.00685}, 253 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00685}, 254 | year = 2021, 255 | month = {oct}, 256 | publisher = {{IEEE}}, 257 | author = {Ruifei He and Jihan Yang and Xiaojuan Qi}, 258 | title = {Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation}, 259 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 260 | } 261 | @inproceedings{Yu_2021, 262 | doi = {10.1109/wacv48630.2021.00330}, 263 | url = {https://doi.org/10.1109%2Fwacv48630.2021.00330}, 264 | year = 2021, 265 | month = {jan}, 266 | publisher = {{IEEE}}, 267 | author = {Weiping Yu and Taojiannan Yang and Chen Chen}, 268 | title = {Towards Resolving the Challenge of Long-tail Distribution in {UAV} Images for Object Detection}, 269 | booktitle = {2021 {IEEE} Winter Conference on Applications of Computer Vision ({WACV})} 270 | } 271 | @inproceedings{Jamal_2020, 272 | doi = {10.1109/cvpr42600.2020.00763}, 273 | url = {https://doi.org/10.1109%2Fcvpr42600.2020.00763}, 274 | year = 2020, 275 | month = {jun}, 276 | publisher = {{IEEE}}, 277 | author = {Muhammad Abdullah Jamal and Matthew Brown and Ming-Hsuan Yang and Liqiang Wang and Boqing Gong}, 278 | title = {Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition From a Domain Adaptation Perspective}, 279 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 280 | } 281 | @inproceedings{Zhang_2021_distr, 282 | doi = {10.1109/cvpr46437.2021.00239}, 283 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.00239}, 284 | year = 2021, 285 | month = {jun}, 286 | publisher = {{IEEE}}, 287 | author = {Songyang Zhang and Zeming Li and Shipeng Yan and Xuming He and Jian Sun}, 288 | title = {Distribution Alignment: A Unified Framework for Long-tail Visual Recognition}, 289 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 290 | } 291 | @article{zhang2021test, 292 | title={Test-agnostic long-tailed recognition by test-time aggregating diverse experts with self-supervision}, 293 | author={Zhang, Yifan and Hooi, Bryan and Hong, Lanqing and Feng, Jiashi}, 294 | journal={arXiv preprint arXiv:2107.09249}, 295 | year={2021} 296 | } 297 | @inproceedings{Hong_2021, 298 | doi = {10.1109/cvpr46437.2021.00656}, 299 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.00656}, 300 | year = 2021, 301 | month = {jun}, 302 | publisher = {{IEEE}}, 303 | author = {Youngkyu Hong and Seungju Han and Kwanghee Choi and Seokjun Seo and Beomsu Kim and Buru Chang}, 304 | title = {Disentangling Label Distribution for Long-tailed Visual Recognition}, 305 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 306 | } 307 | @article{kang2019decoupling, 308 | title={Decoupling representation and classifier for long-tailed recognition}, 309 | author={Kang, Bingyi and Xie, Saining and Rohrbach, Marcus and Yan, Zhicheng and Gordo, Albert and Feng, Jiashi and Kalantidis, Yannis}, 310 | journal={arXiv preprint arXiv:1910.09217}, 311 | year={2019} 312 | } 313 | @inproceedings{Feng_2021, 314 | doi = {10.1109/iccv48922.2021.00340}, 315 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00340}, 316 | year = 2021, 317 | month = {oct}, 318 | publisher = {{IEEE}}, 319 | author = {Chengjian Feng and Yujie Zhong and Weilin Huang}, 320 | title = {Exploring Classification Equilibrium in Long-Tailed Object Detection}, 321 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 322 | } 323 | @incollection{Wang_2020, 324 | doi = {10.1007/978-3-030-58568-6_43}, 325 | url = {https://doi.org/10.1007%2F978-3-030-58568-6_43}, 326 | year = 2020, 327 | publisher = {Springer International Publishing}, 328 | pages = {728--744}, 329 | author = {Tao Wang and Yu Li and Bingyi Kang and Junnan Li and Junhao Liew and Sheng Tang and Steven Hoi and Jiashi Feng}, 330 | title = {The Devil Is in Classification: A Simple Framework for Long-Tail Instance Segmentation}, 331 | booktitle = {Computer Vision {\textendash} {ECCV} 2020} 332 | } 333 | @inproceedings{Weng_2021, 334 | doi = {10.1109/cvpr46437.2021.00263}, 335 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.00263}, 336 | year = 2021, 337 | month = {jun}, 338 | publisher = {{IEEE}}, 339 | author = {Zhenzhen Weng and Mehmet Giray Ogut and Shai Limonchik and Serena Yeung}, 340 | title = {Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision}, 341 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 342 | } 343 | @inproceedings{Gupta_2019, 344 | doi = {10.1109/cvpr.2019.00550}, 345 | url = {https://doi.org/10.1109%2Fcvpr.2019.00550}, 346 | year = 2019, 347 | month = {jun}, 348 | publisher = {{IEEE}}, 349 | author = {Agrim Gupta and Piotr Dollar and Ross Girshick}, 350 | title = {{LVIS}: A Dataset for Large Vocabulary Instance Segmentation}, 351 | booktitle = {2019 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 352 | } 353 | @incollection{Wu_2020_dist, 354 | doi = {10.1007/978-3-030-58548-8_10}, 355 | url = {https://doi.org/10.1007%2F978-3-030-58548-8_10}, 356 | year = 2020, 357 | publisher = {Springer International Publishing}, 358 | pages = {162--178}, 359 | author = {Tong Wu and Qingqiu Huang and Ziwei Liu and Yu Wang and Dahua Lin}, 360 | title = {Distribution-Balanced Loss for Multi-label Classification in Long-Tailed Datasets}, 361 | booktitle = {Computer Vision {\textendash} {ECCV} 2020} 362 | } 363 | @inproceedings{Zhang_2021_video, 364 | doi = {10.1109/iccv48922.2021.00786}, 365 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00786}, 366 | year = 2021, 367 | month = {oct}, 368 | publisher = {{IEEE}}, 369 | author = {Xing Zhang and Zuxuan Wu and Zejia Weng and Huazhu Fu and Jingjing Chen and Yu-Gang Jiang and Larry Davis}, 370 | title = {{VideoLT}: Large-scale Long-tailed Video Recognition}, 371 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 372 | } 373 | @inproceedings{Deng_2009, 374 | doi = {10.1109/cvpr.2009.5206848}, 375 | url = {https://doi.org/10.1109%2Fcvpr.2009.5206848}, 376 | year = 2009, 377 | month = {jun}, 378 | publisher = {{IEEE}}, 379 | author = {Jia Deng and Wei Dong and Richard Socher and Li-Jia Li and Kai Li and Li Fei-Fei}, 380 | title = {{ImageNet}: A large-scale hierarchical image database}, 381 | booktitle = {2009 {IEEE} Conference on Computer Vision and Pattern Recognition} 382 | } 383 | @article{krizhevsky2009learning, 384 | title={Learning multiple layers of features from tiny images}, 385 | author={Krizhevsky, Alex and Hinton, Geoffrey and others}, 386 | year={2009}, 387 | publisher={Citeseer} 388 | } 389 | @article{zhou2014learning, 390 | title={Learning deep features for scene recognition using places database}, 391 | author={Zhou, Bolei and Lapedriza, Agata and Xiao, Jianxiong and Torralba, Antonio and Oliva, Aude}, 392 | journal={Advances in neural information processing systems}, 393 | volume={27}, 394 | year={2014} 395 | } 396 | @article{Everingham_2014, 397 | doi = {10.1007/s11263-014-0733-5}, 398 | url = {https://doi.org/10.1007%2Fs11263-014-0733-5}, 399 | year = 2014, 400 | month = {jun}, 401 | publisher = {Springer Science and Business Media {LLC}}, 402 | volume = {111}, 403 | number = {1}, 404 | pages = {98--136}, 405 | author = {Mark Everingham and S. M. Ali Eslami and Luc Van Gool and Christopher K. I. Williams and John Winn and Andrew Zisserman}, 406 | title = {The Pascal Visual Object Classes Challenge: A Retrospective}, 407 | journal = {International Journal of Computer Vision} 408 | } 409 | @incollection{Lin_2014, 410 | doi = {10.1007/978-3-319-10602-1_48}, 411 | url = {https://doi.org/10.1007%2F978-3-319-10602-1_48}, 412 | year = 2014, 413 | publisher = {Springer International Publishing}, 414 | pages = {740--755}, 415 | author = {Tsung-Yi Lin and Michael Maire and Serge Belongie and James Hays and Pietro Perona and Deva Ramanan and Piotr Doll{\'{a}}r and C. Lawrence Zitnick}, 416 | title = {Microsoft {COCO}: Common Objects in Context}, 417 | booktitle = {Computer Vision {\textendash} {ECCV} 2014} 418 | } 419 | @inproceedings{Rezatofighi_2019, 420 | doi = {10.1109/cvpr.2019.00075}, 421 | url = {https://doi.org/10.1109%2Fcvpr.2019.00075}, 422 | year = 2019, 423 | month = {jun}, 424 | publisher = {{IEEE}}, 425 | author = {Hamid Rezatofighi and Nathan Tsoi and JunYoung Gwak and Amir Sadeghian and Ian Reid and Silvio Savarese}, 426 | title = {Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression}, 427 | booktitle = {2019 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 428 | } 429 | @inproceedings{Xie_2017, 430 | doi = {10.1109/cvpr.2017.634}, 431 | url = {https://doi.org/10.1109%2Fcvpr.2017.634}, 432 | year = 2017, 433 | month = {jul}, 434 | publisher = {{IEEE}}, 435 | author = {Saining Xie and Ross Girshick and Piotr Dollar and Zhuowen Tu and Kaiming He}, 436 | title = {Aggregated Residual Transformations for Deep Neural Networks}, 437 | booktitle = {2017 {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})} 438 | } 439 | @article{He_2020_mask, 440 | doi = {10.1109/tpami.2018.2844175}, 441 | url = {https://doi.org/10.1109%2Ftpami.2018.2844175}, 442 | year = 2020, 443 | month = {feb}, 444 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 445 | volume = {42}, 446 | number = {2}, 447 | pages = {386--397}, 448 | author = {Kaiming He and Georgia Gkioxari and Piotr Dollar and Ross Girshick}, 449 | title = {Mask R-{CNN}}, 450 | journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence} 451 | } 452 | @inproceedings{Lin_2017_feat, 453 | doi = {10.1109/cvpr.2017.106}, 454 | url = {https://doi.org/10.1109%2Fcvpr.2017.106}, 455 | year = 2017, 456 | month = {jul}, 457 | publisher = {{IEEE}}, 458 | author = {Tsung-Yi Lin and Piotr Dollar and Ross Girshick and Kaiming He and Bharath Hariharan and Serge Belongie}, 459 | title = {Feature Pyramid Networks for Object Detection}, 460 | booktitle = {2017 {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})} 461 | } 462 | @inproceedings{Zhou_2020, 463 | doi = {10.1109/cvpr42600.2020.00974}, 464 | url = {https://doi.org/10.1109%2Fcvpr42600.2020.00974}, 465 | year = 2020, 466 | month = {jun}, 467 | publisher = {{IEEE}}, 468 | author = {Boyan Zhou and Quan Cui and Xiu-Shen Wei and Zhao-Min Chen}, 469 | title = {{BBN}: Bilateral-Branch Network With Cumulative Learning for Long-Tailed Visual Recognition}, 470 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 471 | } 472 | @article{Haibo_He_2009, 473 | doi = {10.1109/tkde.2008.239}, 474 | url = {https://doi.org/10.1109%2Ftkde.2008.239}, 475 | year = 2009, 476 | month = {sep}, 477 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 478 | volume = {21}, 479 | number = {9}, 480 | pages = {1263--1284}, 481 | author = {Haibo He and E.A. Garcia}, 482 | title = {Learning from Imbalanced Data}, 483 | journal = {{IEEE} Transactions on Knowledge and Data Engineering} 484 | } 485 | @article{snell2017prototypical, 486 | title={Prototypical networks for few-shot learning}, 487 | author={Snell, Jake and Swersky, Kevin and Zemel, Richard}, 488 | journal={Advances in neural information processing systems}, 489 | volume={30}, 490 | year={2017} 491 | } 492 | @inproceedings{Sung_2018, 493 | doi = {10.1109/cvpr.2018.00131}, 494 | url = {https://doi.org/10.1109%2Fcvpr.2018.00131}, 495 | year = 2018, 496 | month = {jun}, 497 | publisher = {{IEEE}}, 498 | author = {Flood Sung and Yongxin Yang and Li Zhang and Tao Xiang and Philip H.S. Torr and Timothy M. Hospedales}, 499 | title = {Learning to Compare: Relation Network for Few-Shot Learning}, 500 | booktitle = {2018 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition} 501 | } 502 | @inproceedings{Sun_2019, 503 | doi = {10.1109/cvpr.2019.00049}, 504 | url = {https://doi.org/10.1109%2Fcvpr.2019.00049}, 505 | year = 2019, 506 | month = {jun}, 507 | publisher = {{IEEE}}, 508 | author = {Qianru Sun and Yaoyao Liu and Tat-Seng Chua and Bernt Schiele}, 509 | title = {Meta-Transfer Learning for Few-Shot Learning}, 510 | booktitle = {2019 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 511 | } 512 | @article{wang2020generalizing, 513 | title={Generalizing from a few examples: A survey on few-shot learning}, 514 | author={Wang, Yaqing and Yao, Quanming and Kwok, James T and Ni, Lionel M}, 515 | journal={ACM computing surveys (csur)}, 516 | volume={53}, 517 | number={3}, 518 | pages={1--34}, 519 | year={2020}, 520 | publisher={ACM New York, NY, USA} 521 | } 522 | @inproceedings{krueger2021out, 523 | title={Out-of-distribution generalization via risk extrapolation (rex)}, 524 | author={Krueger, David and Caballero, Ethan and Jacobsen, Joern-Henrik and Zhang, Amy and Binas, Jonathan and Zhang, Dinghuai and Le Priol, Remi and Courville, Aaron}, 525 | booktitle={International Conference on Machine Learning}, 526 | pages={5815--5826}, 527 | year={2021}, 528 | organization={PMLR} 529 | } 530 | @article{shen2021towards, 531 | title={Towards out-of-distribution generalization: A survey}, 532 | author={Shen, Zheyan and Liu, Jiashuo and He, Yue and Zhang, Xingxuan and Xu, Renzhe and Yu, Han and Cui, Peng}, 533 | journal={arXiv preprint arXiv:2108.13624}, 534 | year={2021} 535 | } 536 | @article{Pan_2011, 537 | doi = {10.1109/tnn.2010.2091281}, 538 | url = {https://doi.org/10.1109%2Ftnn.2010.2091281}, 539 | year = 2011, 540 | month = {feb}, 541 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 542 | volume = {22}, 543 | number = {2}, 544 | pages = {199--210}, 545 | author = {Sinno Jialin Pan and Ivor W. Tsang and James T. Kwok and Qiang Yang}, 546 | title = {Domain Adaptation via Transfer Component Analysis}, 547 | journal = {{IEEE} Transactions on Neural Networks} 548 | } 549 | @inproceedings{Tzeng_2017, 550 | doi = {10.1109/cvpr.2017.316}, 551 | url = {https://doi.org/10.1109%2Fcvpr.2017.316}, 552 | year = 2017, 553 | month = {jul}, 554 | publisher = {{IEEE}}, 555 | author = {Eric Tzeng and Judy Hoffman and Kate Saenko and Trevor Darrell}, 556 | title = {Adversarial Discriminative Domain Adaptation}, 557 | booktitle = {2017 {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})} 558 | } 559 | @incollection{Zhang_2019, 560 | doi = {10.1007/978-3-030-32239-7_40}, 561 | url = {https://doi.org/10.1007%2F978-3-030-32239-7_40}, 562 | year = 2019, 563 | publisher = {Springer International Publishing}, 564 | pages = {360--368}, 565 | author = {Yifan Zhang and Hanbo Chen and Ying Wei and Peilin Zhao and Jiezhang Cao and Xinjuan Fan and Xiaoying Lou and Hailing Liu and Jinlong Hou and Xiao Han and Jianhua Yao and Qingyao Wu and Mingkui Tan and Junzhou Huang}, 566 | title = {From Whole Slide Imaging to Microscopy: Deep Microscopy Adaptation Network for Histopathology Cancer Image Classification}, 567 | booktitle = {Lecture Notes in Computer Science} 568 | } 569 | @article{Zhang_2020_colla, 570 | doi = {10.1109/tip.2020.3006377}, 571 | url = {https://doi.org/10.1109%2Ftip.2020.3006377}, 572 | year = 2020, 573 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 574 | volume = {29}, 575 | pages = {7834--7844}, 576 | author = {Yifan Zhang and Ying Wei and Qingyao Wu and Peilin Zhao and Shuaicheng Niu and Junzhou Huang and Mingkui Tan}, 577 | title = {Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis}, 578 | journal = {{IEEE} Transactions on Image Processing} 579 | } 580 | @inproceedings{Qiu_2021, 581 | doi = {10.24963/ijcai.2021/402}, 582 | url = {https://doi.org/10.24963%2Fijcai.2021%2F402}, 583 | year = 2021, 584 | month = {aug}, 585 | publisher = {International Joint Conferences on Artificial Intelligence Organization}, 586 | author = {Zhen Qiu and Yifan Zhang and Hongbin Lin and Shuaicheng Niu and Yanxia Liu and Qing Du and Mingkui Tan}, 587 | title = {Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation}, 588 | booktitle = {Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence} 589 | } 590 | @article{Wu_2021_hete, 591 | doi = {10.1109/tip.2021.3094137}, 592 | url = {https://doi.org/10.1109%2Ftip.2021.3094137}, 593 | year = 2021, 594 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 595 | volume = {30}, 596 | pages = {6364--6376}, 597 | author = {Hanrui Wu and Hong Zhu and Yuguang Yan and Jiaju Wu and Yifan Zhang and Michael K. Ng}, 598 | title = {Heterogeneous Domain Adaptation by Information Capturing and Distribution Matching}, 599 | journal = {{IEEE} Transactions on Image Processing} 600 | } 601 | @inproceedings{Li_2017, 602 | doi = {10.1109/iccv.2017.591}, 603 | url = {https://doi.org/10.1109%2Ficcv.2017.591}, 604 | year = 2017, 605 | month = {oct}, 606 | publisher = {{IEEE}}, 607 | author = {Da Li and Yongxin Yang and Yi-Zhe Song and Timothy M. Hospedales}, 608 | title = {Deeper, Broader and Artier Domain Generalization}, 609 | booktitle = {2017 {IEEE} International Conference on Computer Vision ({ICCV})} 610 | } 611 | @inproceedings{Li_2018, 612 | doi = {10.1109/cvpr.2018.00566}, 613 | url = {https://doi.org/10.1109%2Fcvpr.2018.00566}, 614 | year = 2018, 615 | month = {jun}, 616 | publisher = {{IEEE}}, 617 | author = {Haoliang Li and Sinno Jialin Pan and Shiqi Wang and Alex C. Kot}, 618 | title = {Domain Generalization with Adversarial Feature Learning}, 619 | booktitle = {2018 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition} 620 | } 621 | @incollection{Neal_2018, 622 | doi = {10.1007/978-3-030-01231-1_38}, 623 | url = {https://doi.org/10.1007%2F978-3-030-01231-1_38}, 624 | year = 2018, 625 | publisher = {Springer International Publishing}, 626 | pages = {620--635}, 627 | author = {Lawrence Neal and Matthew Olson and Xiaoli Fern and Weng-Keen Wong and Fuxin Li}, 628 | title = {Open Set Learning with Counterfactual Images}, 629 | booktitle = {Computer Vision {\textendash} {ECCV} 2018} 630 | } 631 | @article{Fu_2020, 632 | doi = {10.1109/tpami.2019.2922175}, 633 | url = {https://doi.org/10.1109%2Ftpami.2019.2922175}, 634 | year = 2020, 635 | month = {dec}, 636 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 637 | volume = {42}, 638 | number = {12}, 639 | pages = {3136--3152}, 640 | author = {Yanwei Fu and Xiaomei Wang and Hanze Dong and Yu-Gang Jiang and Meng Wang and Xiangyang Xue and Leonid Sigal}, 641 | title = {Vocabulary-Informed Zero-Shot and Open-Set Learning}, 642 | journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence} 643 | } 644 | @inproceedings{Huang_2016, 645 | doi = {10.1109/cvpr.2016.580}, 646 | url = {https://doi.org/10.1109%2Fcvpr.2016.580}, 647 | year = 2016, 648 | month = {jun}, 649 | publisher = {{IEEE}}, 650 | author = {Chen Huang and Yining Li and Chen Change Loy and Xiaoou Tang}, 651 | title = {Learning Deep Representation for Imbalanced Classification}, 652 | booktitle = {2016 {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})} 653 | } 654 | @inproceedings{Ouyang_2016, 655 | doi = {10.1109/cvpr.2016.100}, 656 | url = {https://doi.org/10.1109%2Fcvpr.2016.100}, 657 | year = 2016, 658 | month = {jun}, 659 | publisher = {{IEEE}}, 660 | author = {Wanli Ouyang and Xiaogang Wang and Cong Zhang and Xiaokang Yang}, 661 | title = {Factors in Finetuning Deep Model for Object Detection with Long-Tail Distribution}, 662 | booktitle = {2016 {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})} 663 | } 664 | @inproceedings{Lin_2017_focal, 665 | doi = {10.1109/iccv.2017.324}, 666 | url = {https://doi.org/10.1109%2Ficcv.2017.324}, 667 | year = 2017, 668 | month = {oct}, 669 | publisher = {{IEEE}}, 670 | author = {Tsung-Yi Lin and Priya Goyal and Ross Girshick and Kaiming He and Piotr Dollar}, 671 | title = {Focal Loss for Dense Object Detection}, 672 | booktitle = {2017 {IEEE} International Conference on Computer Vision ({ICCV})} 673 | } 674 | @inproceedings{Dong_2017, 675 | doi = {10.1109/iccv.2017.205}, 676 | url = {https://doi.org/10.1109%2Ficcv.2017.205}, 677 | year = 2017, 678 | month = {oct}, 679 | publisher = {{IEEE}}, 680 | author = {Qi Dong and Shaogang Gong and Xiatian Zhu}, 681 | title = {Class Rectification Hard Mining for Imbalanced Deep Learning}, 682 | booktitle = {2017 {IEEE} International Conference on Computer Vision ({ICCV})} 683 | } 684 | @article{wang2017learning, 685 | title={Learning to model the tail}, 686 | author={Wang, Yu-Xiong and Ramanan, Deva and Hebert, Martial}, 687 | journal={Advances in Neural Information Processing Systems}, 688 | volume={30}, 689 | year={2017} 690 | } 691 | @inproceedings{Cui_2018, 692 | doi = {10.1109/cvpr.2018.00432}, 693 | url = {https://doi.org/10.1109%2Fcvpr.2018.00432}, 694 | year = 2018, 695 | month = {jun}, 696 | publisher = {{IEEE}}, 697 | author = {Yin Cui and Yang Song and Chen Sun and Andrew Howard and Serge Belongie}, 698 | title = {Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning}, 699 | booktitle = {2018 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition} 700 | } 701 | @inproceedings{Khan_2019, 702 | doi = {10.1109/cvpr.2019.00019}, 703 | url = {https://doi.org/10.1109%2Fcvpr.2019.00019}, 704 | year = 2019, 705 | month = {jun}, 706 | publisher = {{IEEE}}, 707 | author = {Salman Khan and Munawar Hayat and Syed Waqas Zamir and Jianbing Shen and Ling Shao}, 708 | title = {Striking the Right Balance With Uncertainty}, 709 | booktitle = {2019 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 710 | } 711 | @inproceedings{Yin_2019, 712 | doi = {10.1109/cvpr.2019.00585}, 713 | url = {https://doi.org/10.1109%2Fcvpr.2019.00585}, 714 | year = 2019, 715 | month = {jun}, 716 | publisher = {{IEEE}}, 717 | author = {Xi Yin and Xiang Yu and Kihyuk Sohn and Xiaoming Liu and Manmohan Chandraker}, 718 | title = {Feature Transfer Learning for Face Recognition With Under-Represented Data}, 719 | booktitle = {2019 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 720 | } 721 | @inproceedings{Zhong_2019, 722 | doi = {10.1109/cvpr.2019.00800}, 723 | url = {https://doi.org/10.1109%2Fcvpr.2019.00800}, 724 | year = 2019, 725 | month = {jun}, 726 | publisher = {{IEEE}}, 727 | author = {Yaoyao Zhong and Weihong Deng and Mei Wang and Jiani Hu and Jianteng Peng and Xunqiang Tao and Yaohai Huang}, 728 | title = {Unequal-Training for Deep Face Recognition With Long-Tailed Noisy Data}, 729 | booktitle = {2019 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 730 | } 731 | @inproceedings{Wang_2019, 732 | doi = {10.1109/iccv.2019.00512}, 733 | url = {https://doi.org/10.1109%2Ficcv.2019.00512}, 734 | year = 2019, 735 | month = {oct}, 736 | publisher = {{IEEE}}, 737 | author = {Yiru Wang and Weihao Gan and Jie Yang and Wei Wu and Junjie Yan}, 738 | title = {Dynamic Curriculum Learning for Imbalanced Data Classification}, 739 | booktitle = {2019 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 740 | } 741 | @article{shu2019meta, 742 | title={Meta-weight-net: Learning an explicit mapping for sample weighting}, 743 | author={Shu, Jun and Xie, Qi and Yi, Lixuan and Zhao, Qian and Zhou, Sanping and Xu, Zongben and Meng, Deyu}, 744 | journal={Advances in neural information processing systems}, 745 | volume={32}, 746 | year={2019} 747 | } 748 | @inproceedings{Hu_2020, 749 | doi = {10.1109/cvpr42600.2020.01406}, 750 | url = {https://doi.org/10.1109%2Fcvpr42600.2020.01406}, 751 | year = 2020, 752 | month = {jun}, 753 | publisher = {{IEEE}}, 754 | author = {Xinting Hu and Yi Jiang and Kaihua Tang and Jingyuan Chen and Chunyan Miao and Hanwang Zhang}, 755 | title = {Learning to Segment the Tail}, 756 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 757 | } 758 | @inproceedings{Li_2020, 759 | doi = {10.1109/cvpr42600.2020.01100}, 760 | url = {https://doi.org/10.1109%2Fcvpr42600.2020.01100}, 761 | year = 2020, 762 | month = {jun}, 763 | publisher = {{IEEE}}, 764 | author = {Yu Li and Tao Wang and Bingyi Kang and Sheng Tang and Chunfeng Wang and Jintao Li and Jiashi Feng}, 765 | title = {Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax}, 766 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 767 | } 768 | @inproceedings{Kim_2020_m2m, 769 | doi = {10.1109/cvpr42600.2020.01391}, 770 | url = {https://doi.org/10.1109%2Fcvpr42600.2020.01391}, 771 | year = 2020, 772 | month = {jun}, 773 | publisher = {{IEEE}}, 774 | author = {Jaehyung Kim and Jongheon Jeong and Jinwoo Shin}, 775 | title = {M2m: Imbalanced Classification via Major-to-Minor Translation}, 776 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 777 | } 778 | @inproceedings{Liu_2020, 779 | doi = {10.1109/cvpr42600.2020.00304}, 780 | url = {https://doi.org/10.1109%2Fcvpr42600.2020.00304}, 781 | year = 2020, 782 | month = {jun}, 783 | publisher = {{IEEE}}, 784 | author = {Jialun Liu and Yifan Sun and Chuchu Han and Zhaopeng Dou and Wenhui Li}, 785 | title = {Deep Representation Learning on Long-Tailed Data: A Learnable Embedding Augmentation Perspective}, 786 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 787 | } 788 | @inproceedings{Zhu_2020, 789 | doi = {10.1109/cvpr42600.2020.00440}, 790 | url = {https://doi.org/10.1109%2Fcvpr42600.2020.00440}, 791 | year = 2020, 792 | month = {jun}, 793 | publisher = {{IEEE}}, 794 | author = {Linchao Zhu and Yi Yang}, 795 | title = {Inflated Episodic Memory With Region Self-Attention for Long-Tailed Visual Recognition}, 796 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 797 | } 798 | @incollection{Kim_2020_im, 799 | doi = {10.1007/978-3-030-58601-0_25}, 800 | url = {https://doi.org/10.1007%2F978-3-030-58601-0_25}, 801 | year = 2020, 802 | publisher = {Springer International Publishing}, 803 | pages = {411--428}, 804 | author = {Chris Dongjoo Kim and Jinseo Jeong and Gunhee Kim}, 805 | title = {Imbalanced Continual Learning with Partitioning Reservoir Sampling}, 806 | booktitle = {Computer Vision {\textendash} {ECCV} 2020} 807 | } 808 | @incollection{Chu_2020, 809 | doi = {10.1007/978-3-030-58526-6_41}, 810 | url = {https://doi.org/10.1007%2F978-3-030-58526-6_41}, 811 | year = 2020, 812 | publisher = {Springer International Publishing}, 813 | pages = {694--710}, 814 | author = {Peng Chu and Xiao Bian and Shaopeng Liu and Haibin Ling}, 815 | title = {Feature Space Augmentation for Long-Tailed Data}, 816 | booktitle = {Computer Vision {\textendash} {ECCV} 2020} 817 | } 818 | @incollection{Xiang_2020, 819 | doi = {10.1007/978-3-030-58558-7_15}, 820 | url = {https://doi.org/10.1007%2F978-3-030-58558-7_15}, 821 | year = 2020, 822 | publisher = {Springer International Publishing}, 823 | pages = {247--263}, 824 | author = {Liuyu Xiang and Guiguang Ding and Jungong Han}, 825 | title = {Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-Tailed Classification}, 826 | booktitle = {Computer Vision {\textendash} {ECCV} 2020} 827 | } 828 | @incollection{Wu_2020_solv, 829 | doi = {10.1007/978-3-030-58598-3_11}, 830 | url = {https://doi.org/10.1007%2F978-3-030-58598-3_11}, 831 | year = 2020, 832 | publisher = {Springer International Publishing}, 833 | pages = {171--189}, 834 | author = {Tz-Ying Wu and Pedro Morgado and Pei Wang and Chih-Hui Ho and Nuno Vasconcelos}, 835 | title = {Solving Long-Tailed Recognition with~Deep Realistic Taxonomic Classifier}, 836 | booktitle = {Computer Vision {\textendash} {ECCV} 2020} 837 | } 838 | @article{ren2020balanced, 839 | title={Balanced meta-softmax for long-tailed visual recognition}, 840 | author={Ren, Jiawei and Yu, Cunjun and Ma, Xiao and Zhao, Haiyu and Yi, Shuai and others}, 841 | journal={Advances in Neural Information Processing Systems}, 842 | volume={33}, 843 | pages={4175--4186}, 844 | year={2020} 845 | } 846 | @article{tian2020posterior, 847 | title={Posterior re-calibration for imbalanced datasets}, 848 | author={Tian, Junjiao and Liu, Yen-Cheng and Glaser, Nathaniel and Hsu, Yen-Chang and Kira, Zsolt}, 849 | journal={Advances in Neural Information Processing Systems}, 850 | volume={33}, 851 | pages={8101--8113}, 852 | year={2020} 853 | } 854 | @article{tang2020long, 855 | title={Long-tailed classification by keeping the good and removing the bad momentum causal effect}, 856 | author={Tang, Kaihua and Huang, Jianqiang and Zhang, Hanwang}, 857 | journal={Advances in Neural Information Processing Systems}, 858 | volume={33}, 859 | pages={1513--1524}, 860 | year={2020} 861 | } 862 | @article{yang2020rethinking, 863 | title={Rethinking the value of labels for improving class-imbalanced learning}, 864 | author={Yang, Yuzhe and Xu, Zhi}, 865 | journal={Advances in Neural Information Processing Systems}, 866 | volume={33}, 867 | pages={19290--19301}, 868 | year={2020} 869 | } 870 | @inproceedings{Guo_2021, 871 | doi = {10.1109/cvpr46437.2021.01484}, 872 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.01484}, 873 | year = 2021, 874 | month = {jun}, 875 | publisher = {{IEEE}}, 876 | author = {Hao Guo and Song Wang}, 877 | title = {Long-Tailed Multi-Label Visual Recognition by Collaborative Training on Uniform and Re-balanced Samplings}, 878 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 879 | } 880 | @inproceedings{Tan_2021, 881 | doi = {10.1109/cvpr46437.2021.00173}, 882 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.00173}, 883 | year = 2021, 884 | month = {jun}, 885 | publisher = {{IEEE}}, 886 | author = {Jingru Tan and Xin Lu and Gang Zhang and Changqing Yin and Quanquan Li}, 887 | title = {Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection}, 888 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 889 | } 890 | @inproceedings{Wang_2021_seesaw, 891 | doi = {10.1109/cvpr46437.2021.00957}, 892 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.00957}, 893 | year = 2021, 894 | month = {jun}, 895 | publisher = {{IEEE}}, 896 | author = {Jiaqi Wang and Wenwei Zhang and Yuhang Zang and Yuhang Cao and Jiangmiao Pang and Tao Gong and Kai Chen and Ziwei Liu and Chen Change Loy and Dahua Lin}, 897 | title = {Seesaw Loss for Long-Tailed Instance Segmentation}, 898 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 899 | } 900 | @inproceedings{Wang_2021_adap, 901 | doi = {10.1109/cvpr46437.2021.00312}, 902 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.00312}, 903 | year = 2021, 904 | month = {jun}, 905 | publisher = {{IEEE}}, 906 | author = {Tong Wang and Yousong Zhu and Chaoyang Zhao and Wei Zeng and Jinqiao Wang and Ming Tang}, 907 | title = {Adaptive Class Suppression Loss for Long-Tail Object Detection}, 908 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 909 | } 910 | @inproceedings{Deng_2021, 911 | doi = {10.1109/cvpr46437.2021.01036}, 912 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.01036}, 913 | year = 2021, 914 | month = {jun}, 915 | publisher = {{IEEE}}, 916 | author = {Zongyong Deng and Hao Liu and Yaoxing Wang and Chenyang Wang and Zekuan Yu and Xuehong Sun}, 917 | title = {{PML}: Progressive Margin Loss for Long-tailed Age Classification}, 918 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 919 | } 920 | @inproceedings{Wu_2021_adve, 921 | doi = {10.1109/cvpr46437.2021.00855}, 922 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.00855}, 923 | year = 2021, 924 | month = {jun}, 925 | publisher = {{IEEE}}, 926 | author = {Tong Wu and Ziwei Liu and Qingqiu Huang and Yu Wang and Dahua Lin}, 927 | title = {Adversarial Robustness under Long-Tailed Distribution}, 928 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 929 | } 930 | @inproceedings{Zhong_2021, 931 | doi = {10.1109/cvpr46437.2021.01622}, 932 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.01622}, 933 | year = 2021, 934 | month = {jun}, 935 | publisher = {{IEEE}}, 936 | author = {Zhisheng Zhong and Jiequan Cui and Shu Liu and Jiaya Jia}, 937 | title = {Improving Calibration for Long-Tailed Recognition}, 938 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 939 | } 940 | @inproceedings{Wei_2021, 941 | doi = {10.1109/cvpr46437.2021.01071}, 942 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.01071}, 943 | year = 2021, 944 | month = {jun}, 945 | publisher = {{IEEE}}, 946 | author = {Chen Wei and Kihyuk Sohn and Clayton Mellina and Alan Yuille and Fan Yang}, 947 | title = {{CReST}: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning}, 948 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 949 | } 950 | @inproceedings{Changpinyo_2021, 951 | doi = {10.1109/cvpr46437.2021.00356}, 952 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.00356}, 953 | year = 2021, 954 | month = {jun}, 955 | publisher = {{IEEE}}, 956 | author = {Soravit Changpinyo and Piyush Sharma and Nan Ding and Radu Soricut}, 957 | title = {Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts}, 958 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 959 | } 960 | @inproceedings{Wang_2021_rsg, 961 | doi = {10.1109/cvpr46437.2021.00378}, 962 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.00378}, 963 | year = 2021, 964 | month = {jun}, 965 | publisher = {{IEEE}}, 966 | author = {Jianfeng Wang and Thomas Lukasiewicz and Xiaolin Hu and Jianfei Cai and Zhenghua Xu}, 967 | title = {{RSG}: A Simple but Effective Module for Learning Imbalanced Datasets}, 968 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 969 | } 970 | @inproceedings{Li_2021_meta, 971 | doi = {10.1109/cvpr46437.2021.00517}, 972 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.00517}, 973 | year = 2021, 974 | month = {jun}, 975 | publisher = {{IEEE}}, 976 | author = {Shuang Li and Kaixiong Gong and Chi Harold Liu and Yulin Wang and Feng Qiao and Xinjing Cheng}, 977 | title = {{MetaSAug}: Meta Semantic Augmentation for Long-Tailed Visual Recognition}, 978 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 979 | } 980 | @inproceedings{Wang_2021_cons, 981 | doi = {10.1109/cvpr46437.2021.00100}, 982 | url = {https://doi.org/10.1109%2Fcvpr46437.2021.00100}, 983 | year = 2021, 984 | month = {jun}, 985 | publisher = {{IEEE}}, 986 | author = {Peng Wang and Kai Han and Xiu-Shen Wei and Lei Zhang and Lei Wang}, 987 | title = {Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification}, 988 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 989 | } 990 | @inproceedings{Liu_2021, 991 | doi = {10.1109/iccv48922.2021.00810}, 992 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00810}, 993 | year = 2021, 994 | month = {oct}, 995 | publisher = {{IEEE}}, 996 | author = {Bo Liu and Haoxiang Li and Hao Kang and Gang Hua and Nuno Vasconcelos}, 997 | title = {{GistNet}: a Geometric Structure Transfer Network for Long-Tailed Recognition}, 998 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 999 | } 1000 | @inproceedings{Zang_2021, 1001 | doi = {10.1109/iccv48922.2021.00344}, 1002 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00344}, 1003 | year = 2021, 1004 | month = {oct}, 1005 | publisher = {{IEEE}}, 1006 | author = {Yuhang Zang and Chen Huang and Chen Change Loy}, 1007 | title = {{FASA}: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation}, 1008 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1009 | } 1010 | @inproceedings{Cai_2021, 1011 | doi = {10.1109/iccv48922.2021.00018}, 1012 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00018}, 1013 | year = 2021, 1014 | month = {oct}, 1015 | publisher = {{IEEE}}, 1016 | author = {Jiarui Cai and Yizhou Wang and Jenq-Neng Hwang}, 1017 | title = {{ACE}: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot}, 1018 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1019 | } 1020 | @inproceedings{Park_2021, 1021 | doi = {10.1109/iccv48922.2021.00077}, 1022 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00077}, 1023 | year = 2021, 1024 | month = {oct}, 1025 | publisher = {{IEEE}}, 1026 | author = {Seulki Park and Jongin Lim and Younghan Jeon and Jin Young Choi}, 1027 | title = {Influence-Balanced Loss for Imbalanced Visual Classification}, 1028 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1029 | } 1030 | @inproceedings{Li_2021_self, 1031 | doi = {10.1109/iccv48922.2021.00067}, 1032 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00067}, 1033 | year = 2021, 1034 | month = {oct}, 1035 | publisher = {{IEEE}}, 1036 | author = {Tianhao Li and Limin Wang and Gangshan Wu}, 1037 | title = {Self Supervision to Distillation for Long-Tailed Visual Recognition}, 1038 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1039 | } 1040 | @inproceedings{He_2021_dist, 1041 | doi = {10.1109/iccv48922.2021.00030}, 1042 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00030}, 1043 | year = 2021, 1044 | month = {oct}, 1045 | publisher = {{IEEE}}, 1046 | author = {Yin-Yin He and Jianxin Wu and Xiu-Shen Wei}, 1047 | title = {Distilling Virtual Examples for Long-tailed Recognition}, 1048 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1049 | } 1050 | @inproceedings{Zhang_2021_mosa, 1051 | doi = {10.1109/iccv48922.2021.00047}, 1052 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00047}, 1053 | year = 2021, 1054 | month = {oct}, 1055 | publisher = {{IEEE}}, 1056 | author = {Cheng Zhang and Tai-Yu Pan and Yandong Li and Hexiang Hu and Dong Xuan and Soravit Changpinyo and Boqing Gong and Wei-Lun Chao}, 1057 | title = {{MosaicOS}: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection}, 1058 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1059 | } 1060 | @inproceedings{Cui_2021, 1061 | doi = {10.1109/iccv48922.2021.00075}, 1062 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00075}, 1063 | year = 2021, 1064 | month = {oct}, 1065 | publisher = {{IEEE}}, 1066 | author = {Jiequan Cui and Zhisheng Zhong and Shu Liu and Bei Yu and Jiaya Jia}, 1067 | title = {Parametric Contrastive Learning}, 1068 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1069 | } 1070 | @inproceedings{Samuel_2021, 1071 | doi = {10.1109/iccv48922.2021.00936}, 1072 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00936}, 1073 | year = 2021, 1074 | month = {oct}, 1075 | publisher = {{IEEE}}, 1076 | author = {Dvir Samuel and Gal Chechik}, 1077 | title = {Distributional Robustness Loss for Long-tail Learning}, 1078 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1079 | } 1080 | @inproceedings{Desai_2021, 1081 | doi = {10.1109/iccv48922.2021.01512}, 1082 | url = {https://doi.org/10.1109%2Ficcv48922.2021.01512}, 1083 | year = 2021, 1084 | month = {oct}, 1085 | publisher = {{IEEE}}, 1086 | author = {Alakh Desai and Tz-Ying Wu and Subarna Tripathi and Nuno Vasconcelos}, 1087 | title = {Learning of Visual Relations: The Devil is in the Tails}, 1088 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1089 | } 1090 | @article{Chawla_2002, 1091 | doi = {10.1613/jair.953}, 1092 | url = {https://doi.org/10.1613%2Fjair.953}, 1093 | year = 2002, 1094 | month = {jun}, 1095 | publisher = {{AI} Access Foundation}, 1096 | volume = {16}, 1097 | pages = {321--357}, 1098 | author = {N. V. Chawla and K. W. Bowyer and L. O. Hall and W. P. Kegelmeyer}, 1099 | title = {{SMOTE}: Synthetic Minority Over-sampling Technique}, 1100 | journal = {Journal of Artificial Intelligence Research} 1101 | } 1102 | @article{Estabrooks_2004, 1103 | doi = {10.1111/j.0824-7935.2004.t01-1-00228.x}, 1104 | url = {https://doi.org/10.1111%2Fj.0824-7935.2004.t01-1-00228.x}, 1105 | year = 2004, 1106 | month = {feb}, 1107 | publisher = {Wiley}, 1108 | volume = {20}, 1109 | number = {1}, 1110 | pages = {18--36}, 1111 | author = {Andrew Estabrooks and Taeho Jo and Nathalie Japkowicz}, 1112 | title = {A Multiple Resampling Method for Learning from Imbalanced Data Sets}, 1113 | journal = {Computational Intelligence} 1114 | } 1115 | @incollection{Han_2005, 1116 | doi = {10.1007/11538059_91}, 1117 | url = {https://doi.org/10.1007%2F11538059_91}, 1118 | year = 2005, 1119 | publisher = {Springer Berlin Heidelberg}, 1120 | pages = {878--887}, 1121 | author = {Hui Han and Wen-Yuan Wang and Bing-Huan Mao}, 1122 | title = {Borderline-{SMOTE}: A New Over-Sampling Method in Imbalanced Data Sets Learning}, 1123 | booktitle = {Lecture Notes in Computer Science} 1124 | } 1125 | @article{Xu_Ying_Liu_2009, 1126 | doi = {10.1109/tsmcb.2008.2007853}, 1127 | url = {https://doi.org/10.1109%2Ftsmcb.2008.2007853}, 1128 | year = 2009, 1129 | month = {apr}, 1130 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 1131 | volume = {39}, 1132 | number = {2}, 1133 | pages = {539--550}, 1134 | author = {Xu-Ying Liu and Jianxin Wu and Zhi-Hua Zhou}, 1135 | title = {Exploratory Undersampling for Class-Imbalance Learning}, 1136 | journal = {{IEEE} Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)} 1137 | } 1138 | @inproceedings{Zhang_2021_learn, 1139 | doi = {10.1109/iccv48922.2021.00076}, 1140 | url = {https://doi.org/10.1109%2Ficcv48922.2021.00076}, 1141 | year = 2021, 1142 | month = {oct}, 1143 | publisher = {{IEEE}}, 1144 | author = {Zizhao Zhang and Tomas Pfister}, 1145 | title = {Learning Fast Sample Re-weighting Without Reward Data}, 1146 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1147 | } 1148 | @incollection{Mahajan_2018, 1149 | doi = {10.1007/978-3-030-01216-8_12}, 1150 | url = {https://doi.org/10.1007%2F978-3-030-01216-8_12}, 1151 | year = 2018, 1152 | publisher = {Springer International Publishing}, 1153 | pages = {185--201}, 1154 | author = {Dhruv Mahajan and Ross Girshick and Vignesh Ramanathan and Kaiming He and Manohar Paluri and Yixuan Li and Ashwin Bharambe and Laurens van der Maaten}, 1155 | title = {Exploring the Limits of Weakly Supervised Pretraining}, 1156 | booktitle = {Computer Vision {\textendash} {ECCV} 2018} 1157 | } 1158 | @article{hermans2017defense, 1159 | title={In defense of the triplet loss for person re-identification}, 1160 | author={Hermans, Alexander and Beyer, Lucas and Leibe, Bastian}, 1161 | journal={arXiv preprint arXiv:1703.07737}, 1162 | year={2017} 1163 | } 1164 | @inproceedings{elkan2001foundations, 1165 | title={The foundations of cost-sensitive learning}, 1166 | author={Elkan, Charles}, 1167 | booktitle={International joint conference on artificial intelligence}, 1168 | volume={17}, 1169 | number={1}, 1170 | pages={973--978}, 1171 | year={2001}, 1172 | organization={Lawrence Erlbaum Associates Ltd} 1173 | } 1174 | @article{Zhi_Hua_Zhou_2006, 1175 | doi = {10.1109/tkde.2006.17}, 1176 | url = {https://doi.org/10.1109%2Ftkde.2006.17}, 1177 | year = 2006, 1178 | month = {jan}, 1179 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 1180 | volume = {18}, 1181 | number = {1}, 1182 | pages = {63--77}, 1183 | author = {Zhi-Hua Zhou and Xu-Ying Liu}, 1184 | title = {Training cost-sensitive neural networks with methods addressing the class imbalance problem}, 1185 | journal = {{IEEE} Transactions on Knowledge and Data Engineering} 1186 | } 1187 | @article{Sun_2007, 1188 | doi = {10.1016/j.patcog.2007.04.009}, 1189 | url = {https://doi.org/10.1016%2Fj.patcog.2007.04.009}, 1190 | year = 2007, 1191 | month = {dec}, 1192 | publisher = {Elsevier {BV}}, 1193 | volume = {40}, 1194 | number = {12}, 1195 | pages = {3358--3378}, 1196 | author = {Yanmin Sun and Mohamed S. Kamel and Andrew K.C. Wong and Yang Wang}, 1197 | title = {Cost-sensitive boosting for classification of imbalanced data}, 1198 | journal = {Pattern Recognition} 1199 | } 1200 | @article{Zhao_2019, 1201 | doi = {10.1109/tkde.2018.2826011}, 1202 | url = {https://doi.org/10.1109%2Ftkde.2018.2826011}, 1203 | year = 2019, 1204 | month = {feb}, 1205 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 1206 | volume = {31}, 1207 | number = {2}, 1208 | pages = {214--228}, 1209 | author = {Peilin Zhao and Yifan Zhang and Min Wu and Steven C. H. Hoi and Mingkui Tan and Junzhou Huang}, 1210 | title = {Adaptive Cost-Sensitive Online Classification}, 1211 | journal = {{IEEE} Transactions on Knowledge and Data Engineering} 1212 | } 1213 | @inproceedings{Zhang_2018, 1214 | title={Online adaptive asymmetric active learning for budgeted imbalanced data}, 1215 | author={Zhang, Yifan and Zhao, Peilin and Cao, Jiezhang and Ma, Wenye and Huang, Junzhou and Wu, Qingyao and Tan, Mingkui}, 1216 | booktitle={Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining}, 1217 | pages={2768--2777}, 1218 | year={2018} 1219 | } 1220 | @article{Zhang_2021_online, 1221 | doi = {10.1109/tkde.2019.2955078}, 1222 | url = {https://doi.org/10.1109%2Ftkde.2019.2955078}, 1223 | year = 2021, 1224 | month = {jun}, 1225 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 1226 | volume = {33}, 1227 | number = {6}, 1228 | pages = {2680--2692}, 1229 | author = {Yifan Zhang and Peilin Zhao and Shuaicheng Niu and Qingyao Wu and Jiezhang Cao and Junzhou Huang and Mingkui Tan}, 1230 | title = {Online Adaptive Asymmetric Active Learning With Limited Budgets}, 1231 | journal = {{IEEE} Transactions on Knowledge and Data Engineering} 1232 | } 1233 | @article{ye2020identifying, 1234 | title={Identifying and compensating for feature deviation in imbalanced deep learning}, 1235 | author={Ye, Han-Jia and Chen, Hong-You and Zhan, De-Chuan and Chao, Wei-Lun}, 1236 | journal={arXiv preprint arXiv:2001.01385}, 1237 | year={2020} 1238 | } 1239 | @inproceedings{hsieh2021droploss, 1240 | title={Droploss for long-tail instance segmentation}, 1241 | author={Hsieh, Ting-I and Robb, Esther and Chen, Hwann-Tzong and Huang, Jia-Bin}, 1242 | booktitle={AAAI}, 1243 | volume={3}, 1244 | number={6}, 1245 | pages={15}, 1246 | year={2021} 1247 | } 1248 | @article{Wang_2018, 1249 | doi = {10.1109/lsp.2018.2822810}, 1250 | url = {https://doi.org/10.1109%2Flsp.2018.2822810}, 1251 | year = 2018, 1252 | month = {jul}, 1253 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 1254 | volume = {25}, 1255 | number = {7}, 1256 | pages = {926--930}, 1257 | author = {Feng Wang and Jian Cheng and Weiyang Liu and Haijun Liu}, 1258 | title = {Additive Margin Softmax for Face Verification}, 1259 | journal = {{IEEE} Signal Processing Letters} 1260 | } 1261 | @article{Koltchinskii_2002, 1262 | doi = {10.1214/aos/1015362183}, 1263 | url = {https://doi.org/10.1214%2Faos%2F1015362183}, 1264 | year = 2002, 1265 | month = {feb}, 1266 | publisher = {Institute of Mathematical Statistics}, 1267 | volume = {30}, 1268 | number = {1}, 1269 | author = {V. Koltchinskii and D. Panchenko}, 1270 | title = {Empirical Margin Distributions and Bounding the Generalization Error of Combined Classifiers}, 1271 | journal = {The Annals of Statistics} 1272 | } 1273 | @inproceedings{provost2000machine, 1274 | title={Machine learning from imbalanced data sets 101}, 1275 | author={Provost, Foster}, 1276 | booktitle={Proceedings of the AAAI’2000 workshop on imbalanced data sets}, 1277 | volume={68}, 1278 | number={2000}, 1279 | pages={1--3}, 1280 | year={2000}, 1281 | organization={AAAI Press} 1282 | } 1283 | @article{Pan_2010, 1284 | doi = {10.1109/tkde.2009.191}, 1285 | url = {https://doi.org/10.1109%2Ftkde.2009.191}, 1286 | year = 2010, 1287 | month = {oct}, 1288 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 1289 | volume = {22}, 1290 | number = {10}, 1291 | pages = {1345--1359}, 1292 | author = {Sinno Jialin Pan and Qiang Yang}, 1293 | title = {A Survey on Transfer Learning}, 1294 | journal = {{IEEE} Transactions on Knowledge and Data Engineering} 1295 | } 1296 | @incollection{Tan_2018, 1297 | doi = {10.1007/978-3-030-01424-7_27}, 1298 | url = {https://doi.org/10.1007%2F978-3-030-01424-7_27}, 1299 | year = 2018, 1300 | publisher = {Springer International Publishing}, 1301 | pages = {270--279}, 1302 | author = {Chuanqi Tan and Fuchun Sun and Tao Kong and Wenchang Zhang and Chao Yang and Chunfang Liu}, 1303 | title = {A Survey on Deep Transfer Learning}, 1304 | booktitle = {Artificial Neural Networks and Machine Learning {\textendash} {ICANN} 2018} 1305 | } 1306 | @inproceedings{Zhou_2016, 1307 | doi = {10.1109/cvpr.2016.319}, 1308 | url = {https://doi.org/10.1109%2Fcvpr.2016.319}, 1309 | year = 2016, 1310 | month = {jun}, 1311 | publisher = {{IEEE}}, 1312 | author = {Bolei Zhou and Aditya Khosla and Agata Lapedriza and Aude Oliva and Antonio Torralba}, 1313 | title = {Learning Deep Features for Discriminative Localization}, 1314 | booktitle = {2016 {IEEE} Conference on Computer Vision and Pattern Recognition ({CVPR})} 1315 | } 1316 | @inproceedings{erhan2010does, 1317 | title={Why does unsupervised pre-training help deep learning?}, 1318 | author={Erhan, Dumitru and Courville, Aaron and Bengio, Yoshua and Vincent, Pascal}, 1319 | booktitle={Proceedings of the thirteenth international conference on artificial intelligence and statistics}, 1320 | pages={201--208}, 1321 | year={2010}, 1322 | organization={JMLR Workshop and Conference Proceedings} 1323 | } 1324 | @inproceedings{He_2019, 1325 | doi = {10.1109/iccv.2019.00502}, 1326 | url = {https://doi.org/10.1109%2Ficcv.2019.00502}, 1327 | year = 2019, 1328 | month = {oct}, 1329 | publisher = {{IEEE}}, 1330 | author = {Kaiming He and Ross Girshick and Piotr Dollar}, 1331 | title = {Rethinking {ImageNet} Pre-Training}, 1332 | booktitle = {2019 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1333 | } 1334 | @inproceedings{hendrycks2019using, 1335 | title={Using pre-training can improve model robustness and uncertainty}, 1336 | author={Hendrycks, Dan and Lee, Kimin and Mazeika, Mantas}, 1337 | booktitle={International Conference on Machine Learning}, 1338 | pages={2712--2721}, 1339 | year={2019}, 1340 | organization={PMLR} 1341 | } 1342 | @article{zoph2020rethinking, 1343 | title={Rethinking pre-training and self-training}, 1344 | author={Zoph, Barret and Ghiasi, Golnaz and Lin, Tsung-Yi and Cui, Yin and Liu, Hanxiao and Cubuk, Ekin Dogus and Le, Quoc}, 1345 | journal={Advances in neural information processing systems}, 1346 | volume={33}, 1347 | pages={3833--3845}, 1348 | year={2020} 1349 | } 1350 | @article{zhang2021unleashing, 1351 | title={Unleashing the power of contrastive self-supervised visual models via contrast-regularized fine-tuning}, 1352 | author={Zhang, Yifan and Hooi, Bryan and Hu, Dapeng and Liang, Jian and Feng, Jiashi}, 1353 | journal={Advances in Neural Information Processing Systems}, 1354 | volume={34}, 1355 | year={2021} 1356 | } 1357 | @inproceedings{He_2020_momentum, 1358 | doi = {10.1109/cvpr42600.2020.00975}, 1359 | url = {https://doi.org/10.1109%2Fcvpr42600.2020.00975}, 1360 | year = 2020, 1361 | month = {jun}, 1362 | publisher = {{IEEE}}, 1363 | author = {Kaiming He and Haoqi Fan and Yuxin Wu and Saining Xie and Ross Girshick}, 1364 | title = {Momentum Contrast for Unsupervised Visual Representation Learning}, 1365 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 1366 | } 1367 | @article{gidaris2018unsupervised, 1368 | title={Unsupervised representation learning by predicting image rotations}, 1369 | author={Gidaris, Spyros and Singh, Praveer and Komodakis, Nikos}, 1370 | journal={arXiv preprint arXiv:1803.07728}, 1371 | year={2018} 1372 | } 1373 | @article{karthik2021learning, 1374 | title={Learning from long-tailed data with noisy labels}, 1375 | author={Karthik, Shyamgopal and Revaud, J{\'e}rome and Chidlovskii, Boris}, 1376 | journal={arXiv preprint arXiv:2108.11096}, 1377 | year={2021} 1378 | } 1379 | @article{hinton2015distilling, 1380 | title={Distilling the knowledge in a neural network}, 1381 | author={Hinton, Geoffrey and Vinyals, Oriol and Dean, Jeff and others}, 1382 | journal={arXiv preprint arXiv:1503.02531}, 1383 | volume={2}, 1384 | number={7}, 1385 | year={2015} 1386 | } 1387 | @article{Gou_2021, 1388 | doi = {10.1007/s11263-021-01453-z}, 1389 | url = {https://doi.org/10.1007%2Fs11263-021-01453-z}, 1390 | year = 2021, 1391 | month = {mar}, 1392 | publisher = {Springer Science and Business Media {LLC}}, 1393 | volume = {129}, 1394 | number = {6}, 1395 | pages = {1789--1819}, 1396 | author = {Jianping Gou and Baosheng Yu and Stephen J. Maybank and Dacheng Tao}, 1397 | title = {Knowledge Distillation: A Survey}, 1398 | journal = {International Journal of Computer Vision} 1399 | } 1400 | @article{zhu2005semi, 1401 | title={Semi-supervised learning literature survey}, 1402 | author={Zhu, Xiaojin Jerry}, 1403 | year={2005}, 1404 | publisher={University of Wisconsin-Madison Department of Computer Sciences} 1405 | } 1406 | @inproceedings{Rosenberg_2005, 1407 | doi = {10.1109/acvmot.2005.107}, 1408 | url = {https://doi.org/10.1109%2Facvmot.2005.107}, 1409 | year = 2005, 1410 | month = {jan}, 1411 | publisher = {{IEEE}}, 1412 | author = {C. Rosenberg and M. Hebert and H. Schneiderman}, 1413 | title = {Semi-Supervised Self-Training of Object Detection Models}, 1414 | booktitle = {2005 Seventh {IEEE} Workshops on Applications of Computer Vision ({WACV}/{MOTION}{\textquotesingle}05) - Volume 1} 1415 | } 1416 | @article{wei2021robust, 1417 | title={Robust long-tailed learning under label noise}, 1418 | author={Wei, Tong and Shi, Jiang-Xin and Tu, Wei-Wei and Li, Yu-Feng}, 1419 | journal={arXiv preprint arXiv:2108.11569}, 1420 | year={2021} 1421 | } 1422 | @article{perez2017effectiveness, 1423 | title={The effectiveness of data augmentation in image classification using deep learning}, 1424 | author={Perez, Luis and Wang, Jason}, 1425 | journal={arXiv preprint arXiv:1712.04621}, 1426 | year={2017} 1427 | } 1428 | @article{Shorten_2019, 1429 | doi = {10.1186/s40537-019-0197-0}, 1430 | url = {https://doi.org/10.1186%2Fs40537-019-0197-0}, 1431 | year = 2019, 1432 | month = {jul}, 1433 | publisher = {Springer Science and Business Media {LLC}}, 1434 | volume = {6}, 1435 | number = {1}, 1436 | author = {Connor Shorten and Taghi M. Khoshgoftaar}, 1437 | title = {A survey on Image Data Augmentation for Deep Learning}, 1438 | journal = {Journal of Big Data} 1439 | } 1440 | @incollection{Chou_2020, 1441 | doi = {10.1007/978-3-030-65414-6_9}, 1442 | url = {https://doi.org/10.1007%2F978-3-030-65414-6_9}, 1443 | year = 2020, 1444 | publisher = {Springer International Publishing}, 1445 | pages = {95--110}, 1446 | author = {Hsin-Ping Chou and Shih-Chieh Chang and Jia-Yu Pan and Wei Wei and Da-Cheng Juan}, 1447 | title = {Remix: Rebalanced Mixup}, 1448 | booktitle = {Computer Vision {\textendash} {ECCV} 2020 Workshops} 1449 | } 1450 | @article{wang2019implicit, 1451 | title={Implicit semantic data augmentation for deep networks}, 1452 | author={Wang, Yulin and Pan, Xuran and Song, Shiji and Zhang, Hong and Huang, Gao and Wu, Cheng}, 1453 | journal={Advances in Neural Information Processing Systems}, 1454 | volume={32}, 1455 | year={2019} 1456 | } 1457 | @article{Goh_2010, 1458 | doi = {10.1287/opre.1090.0795}, 1459 | url = {https://doi.org/10.1287%2Fopre.1090.0795}, 1460 | year = 2010, 1461 | month = {aug}, 1462 | publisher = {Institute for Operations Research and the Management Sciences ({INFORMS})}, 1463 | volume = {58}, 1464 | number = {4-part-1}, 1465 | pages = {902--917}, 1466 | author = {Joel Goh and Melvyn Sim}, 1467 | title = {Distributionally Robust Optimization and Its Tractable Approximations}, 1468 | journal = {Operations Research} 1469 | } 1470 | @article{Cover_1967, 1471 | doi = {10.1109/tit.1967.1053964}, 1472 | url = {https://doi.org/10.1109%2Ftit.1967.1053964}, 1473 | year = 1967, 1474 | month = {jan}, 1475 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 1476 | volume = {13}, 1477 | number = {1}, 1478 | pages = {21--27}, 1479 | author = {T. Cover and P. Hart}, 1480 | title = {Nearest neighbor pattern classification}, 1481 | journal = {{IEEE} Transactions on Information Theory} 1482 | } 1483 | @article{Cui_2022, 1484 | doi = {10.1109/tpami.2022.3174892}, 1485 | url = {https://doi.org/10.1109%2Ftpami.2022.3174892}, 1486 | year = 2022, 1487 | publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, 1488 | pages = {1--1}, 1489 | author = {Jiequan Cui and Shu Liu and Zhuotao Tian and Zhisheng Zhong and Jiaya Jia}, 1490 | title = {{ResLT}: Residual Learning for Long-tailed Recognition}, 1491 | journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence} 1492 | } 1493 | @inproceedings{Cubuk_2020, 1494 | doi = {10.1109/cvprw50498.2020.00359}, 1495 | url = {https://doi.org/10.1109%2Fcvprw50498.2020.00359}, 1496 | year = 2020, 1497 | month = {jun}, 1498 | publisher = {{IEEE}}, 1499 | author = {Ekin D. Cubuk and Barret Zoph and Jonathon Shlens and Quoc V. Le}, 1500 | title = {Randaugment: Practical automated data augmentation with a reduced search space}, 1501 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition Workshops ({CVPRW})} 1502 | } 1503 | @inproceedings{Yun_2019, 1504 | doi = {10.1109/iccv.2019.00612}, 1505 | url = {https://doi.org/10.1109%2Ficcv.2019.00612}, 1506 | year = 2019, 1507 | month = {oct}, 1508 | publisher = {{IEEE}}, 1509 | author = {Sangdoo Yun and Dongyoon Han and Sanghyuk Chun and Seong Joon Oh and Youngjoon Yoo and Junsuk Choe}, 1510 | title = {{CutMix}: Regularization Strategy to Train Strong Classifiers With Localizable Features}, 1511 | booktitle = {2019 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1512 | } 1513 | @article{keaton2021fine, 1514 | title={Fine-grained visual classification of plant species in the wild: Object detection as a reinforced means of attention}, 1515 | author={Keaton, Matthew R and Zaveri, Ram J and Kovur, Meghana and Henderson, Cole and Adjeroh, Donald A and Doretto, Gianfranco}, 1516 | journal={arXiv preprint arXiv:2106.02141}, 1517 | year={2021} 1518 | } 1519 | @article{jia2021effective, 1520 | title={An Effective and Robust Detector for Logo Detection}, 1521 | author={Jia, Xiaojun and Yan, Huanqian and Wu, Yonglin and Wei, Xingxing and Cao, Xiaochun and Zhang, Yong}, 1522 | journal={arXiv preprint arXiv:2108.00422}, 1523 | year={2021} 1524 | } 1525 | @article{zhang2021rail, 1526 | title={Rail-5k: a Real-World Dataset for Rail Surface Defects Detection}, 1527 | author={Zhang, Zihao and Yu, Shaozuo and Yang, Siwei and Zhou, Yu and Zhao, Bingchen}, 1528 | journal={arXiv preprint arXiv:2106.14366}, 1529 | year={2021} 1530 | } 1531 | @incollection{Galdran_2021, 1532 | doi = {10.1007/978-3-030-87240-3_31}, 1533 | url = {https://doi.org/10.1007%2F978-3-030-87240-3_31}, 1534 | year = 2021, 1535 | publisher = {Springer International Publishing}, 1536 | pages = {323--333}, 1537 | author = {Adrian Galdran and Gustavo Carneiro and Miguel A. Gonz{\'{a}}lez Ballester}, 1538 | title = {Balanced-{MixUp} for Highly Imbalanced Medical Image Classification}, 1539 | booktitle = {Medical Image Computing and Computer Assisted Intervention {\textendash} {MICCAI} 2021} 1540 | } 1541 | @inproceedings{Weyand_2020, 1542 | doi = {10.1109/cvpr42600.2020.00265}, 1543 | url = {https://doi.org/10.1109%2Fcvpr42600.2020.00265}, 1544 | year = 2020, 1545 | month = {jun}, 1546 | publisher = {{IEEE}}, 1547 | author = {Tobias Weyand and Andre Araujo and Bingyi Cao and Jack Sim}, 1548 | title = {Google Landmarks Dataset v2 {\textendash} A Large-Scale Benchmark for Instance-Level Recognition and Retrieval}, 1549 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 1550 | } 1551 | @inproceedings{Wu_2020_fore, 1552 | doi = {10.1145/3394171.3413970}, 1553 | url = {https://doi.org/10.1145%2F3394171.3413970}, 1554 | year = 2020, 1555 | month = {oct}, 1556 | publisher = {{ACM}}, 1557 | author = {Jialian Wu and Liangchen Song and Tiancai Wang and Qian Zhang and Junsong Yuan}, 1558 | title = {Forest R-{CNN}: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation}, 1559 | booktitle = {Proceedings of the 28th {ACM} International Conference on Multimedia} 1560 | } 1561 | @article{mao2021one, 1562 | title={One million scenes for autonomous driving: Once dataset}, 1563 | author={Mao, Jiageng and Niu, Minzhe and Jiang, Chenhan and Liang, Hanxue and Chen, Jingheng and Liang, Xiaodan and Li, Yamin and Ye, Chaoqiang and Zhang, Wei and Li, Zhenguo and others}, 1564 | journal={arXiv preprint arXiv:2106.11037}, 1565 | year={2021} 1566 | } 1567 | @inproceedings{Zhang_2020_polar, 1568 | doi = {10.1109/cvpr42600.2020.00962}, 1569 | url = {https://doi.org/10.1109%2Fcvpr42600.2020.00962}, 1570 | year = 2020, 1571 | month = {jun}, 1572 | publisher = {{IEEE}}, 1573 | author = {Yang Zhang and Zixiang Zhou and Philip David and Xiangyu Yue and Zerong Xi and Boqing Gong and Hassan Foroosh}, 1574 | title = {{PolarNet}: An Improved Grid Representation for Online {LiDAR} Point Clouds Semantic Segmentation}, 1575 | booktitle = {2020 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})} 1576 | } 1577 | @article{chen2020compositional, 1578 | title={Compositional prototype network with multi-view comparision for few-shot point cloud semantic segmentation}, 1579 | author={Chen, Xiaoyu and Zhang, Chi and Lin, Guosheng and Han, Jing}, 1580 | journal={arXiv preprint arXiv:2012.14255}, 1581 | year={2020} 1582 | } 1583 | @inproceedings{Dhingra_2021, 1584 | doi = {10.1109/cvprw53098.2021.00244}, 1585 | url = {https://doi.org/10.1109%2Fcvprw53098.2021.00244}, 1586 | year = 2021, 1587 | month = {jun}, 1588 | publisher = {{IEEE}}, 1589 | author = {Naina Dhingra and Florian Ritter and Andreas Kunz}, 1590 | title = {{BGT}-Net: Bidirectional {GRU} Transformer Network for Scene Graph Generation}, 1591 | booktitle = {2021 {IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition Workshops ({CVPRW})} 1592 | } 1593 | @article{chen2021reltransformer, 1594 | title={RelTransformer: Balancing the Visual Relationship Detection from Local Context, Scene and Memory}, 1595 | author={Chen, Jun and Agarwal, Aniket and Abdelkarim, Sherif and Zhu, Deyao and Elhoseiny, Mohamed}, 1596 | journal={arXiv preprint arXiv:2104.11934}, 1597 | year={2021} 1598 | } 1599 | @inproceedings{Li_2021_cali, 1600 | doi = {10.1109/iccv48922.2021.01464}, 1601 | url = {https://doi.org/10.1109%2Ficcv48922.2021.01464}, 1602 | year = 2021, 1603 | month = {oct}, 1604 | publisher = {{IEEE}}, 1605 | author = {Zhuowan Li and Elias Stengel-Eskin and Yixiao Zhang and Cihang Xie and Quan Tran and Benjamin Van Durme and Alan Yuille}, 1606 | title = {Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images}, 1607 | booktitle = {2021 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1608 | } 1609 | @article{luo2021no, 1610 | title={No fear of heterogeneity: Classifier calibration for federated learning with non-iid data}, 1611 | author={Luo, Mi and Chen, Fei and Hu, Dapeng and Zhang, Yifan and Liang, Jian and Feng, Jiashi}, 1612 | journal={Advances in Neural Information Processing Systems}, 1613 | volume={34}, 1614 | year={2021} 1615 | } 1616 | @inproceedings{niu2021adaxpert, 1617 | title={Adaxpert: Adapting neural architecture for growing data}, 1618 | author={Niu, Shuaicheng and Wu, Jiaxiang and Xu, Guanghui and Zhang, Yifan and Guo, Yong and Zhao, Peilin and Wang, Peng and Tan, Mingkui}, 1619 | booktitle={International Conference on Machine Learning}, 1620 | pages={8184--8194}, 1621 | year={2021}, 1622 | organization={PMLR} 1623 | } 1624 | @article{zhang2020covid, 1625 | title={Covid-da: deep domain adaptation from typical pneumonia to covid-19}, 1626 | author={Zhang, Yifan and Niu, Shuaicheng and Qiu, Zhen and Wei, Ying and Zhao, Peilin and Yao, Jianhua and Huang, Junzhou and Wu, Qingyao and Tan, Mingkui}, 1627 | journal={arXiv preprint arXiv:2005.01577}, 1628 | year={2020} 1629 | } 1630 | @inproceedings{Peng_2019, 1631 | doi = {10.1109/iccv.2019.00149}, 1632 | url = {https://doi.org/10.1109%2Ficcv.2019.00149}, 1633 | year = 2019, 1634 | month = {oct}, 1635 | publisher = {{IEEE}}, 1636 | author = {Xingchao Peng and Qinxun Bai and Xide Xia and Zijun Huang and Kate Saenko and Bo Wang}, 1637 | title = {Moment Matching for Multi-Source Domain Adaptation}, 1638 | booktitle = {2019 {IEEE}/{CVF} International Conference on Computer Vision ({ICCV})} 1639 | } 1640 | @article{cao2020heteroskedastic, 1641 | title={Heteroskedastic and imbalanced deep learning with adaptive regularization}, 1642 | author={Cao, Kaidi and Chen, Yining and Lu, Junwei and Arechiga, Nikos and Gaidon, Adrien and Ma, Tengyu}, 1643 | journal={arXiv preprint arXiv:2006.15766}, 1644 | year={2020} 1645 | } 1646 | @inproceedings{yang2021delving, 1647 | title={Delving into deep imbalanced regression}, 1648 | author={Yang, Yuzhe and Zha, Kaiwen and Chen, Yingcong and Wang, Hao and Katabi, Dina}, 1649 | booktitle={International Conference on Machine Learning}, 1650 | pages={11842--11851}, 1651 | year={2021}, 1652 | organization={PMLR} 1653 | } --------------------------------------------------------------------------------