└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Deep-Learning-Papers-Reading-List 2 | ## Table of Contents 3 | - [Papers](#papers) 4 | - [Datasets](#datasets) 5 | - [Software and Skills](#software-and-skills) 6 | 7 | ## Papers 8 | ### Recognition 9 | - Handwritten Digit Recognition with a Back-Propagation Network(**LeNet**) [[paper]](http://yann.lecun.com/exdb/publis/pdf/lecun-90c.pdf) 10 | - ImageNet Classification with Deep Convolutional Neural Networks(**AlexNet**) [[paper]](https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf) 11 | - Deep Sparse Rectifier Neural Networks(**ReLU**) [paper](http://proceedings.mlr.press/v15/glorot11a.html) 12 | - Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift(**Batch-Norm**) [[paper]](https://arxiv.org/abs/1502.03167) 13 | - Dropout: A Simple Way to Prevent Neural Networks from Overfitting(**Dropout**) [[paper]](http://jmlr.org/papers/v15/srivastava14a.html) 14 | - Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition(**SPP**) [[paper]](https://arxiv.org/abs/1406.4729) 15 | - Very Deep Convolutional Networks For Large-Scale Image Recognition(**VGG**) [[paper]](https://arxiv.org/abs/1409.1556) 16 | - Network In Network 17 | - Highway Networks 18 | - Going Deeper with Convolutions(**GoogleNet**) 19 | - Rethinking the Inception Architecture for Computer Vision(**Inception v3**) [[paper]](https://arxiv.org/abs/1512.00567) 20 | - PolyNet: A Pursuit of Structural Diversity in Very Deep Networks(**PolyNet**) [[paper]](https://arxiv.org/abs/1611.05725) 21 | - PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection(**PVANet**) [[paper]](https://arxiv.org/abs/1608.08021) 22 | - Deep Residual Learning for Image Recognition(**ResNet**) 23 | - Identity Mappings in Deep Residual Networks 24 | - Wide Residual Networks(**Wide-ResNet**) 25 | - Aggregated Residual Transformations for Deep Neural Networks 26 | - Xception: Deep Learning with Depthwise Separable Convolutions(**Xception**) [[paper]](https://arxiv.org/abs/1610.02357) 27 | - Densely Connected Convolutional Networks(**DenseNet**) 28 | - Squeeze-and-Excitation Networks(**SENet**) [[paper]](https://arxiv.org/abs/1709.01507) 29 | - MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications(**MobileNet**) [[paper]](https://arxiv.org/abs/1704.04861) 30 | - ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices(**ShuffleNet**) [[paper]](https://arxiv.org/abs/1707.01083) 31 | 32 | ### Detection 33 | - Rich feature hierarchies for accurate object detection and semantic segmentation(**RCNN**) 34 | - Fast R-CNN 35 | - Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks 36 | - DenseBox: Unifying Landmark Localization with End to End Object Detection(**DenseBox**) [[paper]](https://arxiv.org/abs/1509.04874) 37 | - You Only Look Once: Unified, Real-Time Object Detection(**YOLO**) [[paper]](https://arxiv.org/abs/1506.02640) 38 | - SSD: Single Shot MultiBox Detector(**SSD**) [[paper]](https://arxiv.org/abs/1512.02325) 39 | - DSSD : Deconvolutional Single Shot Detector(**DSSD**) [[paper]](https://arxiv.org/abs/1701.06659) 40 | - R-FCN: Object Detection via Region-based Fully Convolutional Networks(**RFCN**) [[paper]](https://arxiv.org/abs/1605.06409) 41 | - Feature Pyramid Networks for Object Detection(**FPN**) [[paper]](https://arxiv.org/abs/1612.03144) 42 | - Mask R-CNN [[paper]](https://arxiv.org/abs/1703.06870) 43 | - Focal Loss for Dense Object Detection(**RetinaNet**) [[paper]](https://arxiv.org/abs/1708.02002) 44 | - RON: Reverse Connection with Objectness Prior Networks for Object Detection(**RON**) [[paper]](https://arxiv.org/abs/1707.01691) 45 | - Deformable Convolutional Networks [[paper]](https://arxiv.org/abs/1703.06211) 46 | - Single-Shot Refinement Neural Network for Object Detection [[paper]](https://arxiv.org/abs/1711.06897) 47 | - Light-Head R-CNN: In Defense of Two-Stage Object Detector [[paper]](https://arxiv.org/abs/1711.07264) 48 | 49 | ### Segmentation 50 | #### semantic segmentation 51 | - Fully Convolutional Networks for Semantic Segmentation(**FCN**) 52 | - Learning Deconvolution Network for Semantic Segmentation(**Deconv**) 53 | - Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials 54 | - Conditional Random Fields as Recurrent Neural Networks(**CRFasRNN**) 55 | - Semantic Image Segmentation via Deep Parsing Network(**DPN**) 56 | - Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation 57 | - Exploring Context with Deep Structured models for Semantic Segmentation 58 | - Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs(**Deeplab v1**) 59 | - DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution,and Fully Connected CRFs(**Deeplab v2**) 60 | - RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation(**RefineNet**) 61 | - Understanding Convolution for Semantic Segmentation(**DUC**) 62 | - Wider or Deeper: Revisiting the ResNet Model for Visual Recognition 63 | - Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade 64 | - Loss Max-Pooling for Semantic Image Segmentation 65 | - Pyramid Scene Parsing Network(**PSPNet**) 66 | - Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network(**GCN**) 67 | - Rethinking Atrous Convolution for Semantic Image Segmentation(**Deeplab v3**) 68 | - Global-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions 69 | - Stacked Deconvolutional Network for Semantic Segmentation(**SDN**) 70 | - Learning a Discriminative Feature Network for Semantic Segmentation(**DFN**)[[paper]](https://arxiv.org/abs/1804.09337) 71 | - DenseASPP for Semantic Segmentation in Street Scenes 72 | - Context Encoding for Semantic Segmentation 73 | - Dynamic-structured Semantic Propagation Network 74 | - The Lovasz-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks 75 | - Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation 76 | 77 | #### instance segmentation 78 | - Instance-aware Semantic Segmentation via Multi-task Network Cascades(**MNC**) [[paper]](https://arxiv.org/abs/1512.04412) 79 | - Proposal-free Network for Instance-level Object Segmentation [[paper]](https://arxiv.org/abs/1509.02636) 80 | - Learning to Segment Object Candidates(**DeepMask**) [[paper]](https://arxiv.org/abs/1506.06204) 81 | - Learning to Refine Object Segments(**SharpMask**) [[paper]](https://arxiv.org/abs/1603.08695) 82 | - FastMask: Segment Multi-scale Object Candidates in One Shot(**FastMask**) [[paper]](https://arxiv.org/abs/1612.08843) 83 | - Instance-sensitive Fully Convolutional Networks(**Instance-sensitive FCN**) [[paper]](https://arxiv.org/abs/1603.08678) 84 | - Associative Embedding: End-to-End Learning for Joint Detection and Grouping [[paper]](https://arxiv.org/abs/1611.05424) 85 | - Fully Convolutional Instance-aware Semantic Segmentation(**FCIS**) [[paper]](https://arxiv.org/abs/1611.07709) 86 | - Mask R-CNN [[paper]](https://arxiv.org/abs/1703.06870) 87 | - Learning to Segment Every Thing [[paper]](https://arxiv.org/abs/1711.10370) 88 | - MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features [[paper]](https://arxiv.org/abs/1712.04837v1) 89 | 90 | #### fast segmentation 91 | - SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation(**SegNet**) 92 | - ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation(**ENet**) 93 | - ICNet for Real-Time Semantic Segmentation(**ICNet**) 94 | - LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation(**ICNet**) 95 | - Efficient ConvNet for real-Time semantic segmentation 96 | - Real-time Semantic Image Segmentation via Spatial Sparsity 97 | 98 | #### video segmentation 99 | - Video Propagation Networks 100 | - One-Shot Video Object Segmentation 101 | - Learning Video Object Segmentation from Static Images 102 | - SegFlow: Joint Learning for Video Object Segmentation and Optical Flow 103 | - Online Adaptation of Convolutional Neural Networks for Video Object Segmentation 104 | - Lucid Data Dreaming for Object Tracking 105 | - Lucid Data Dreaming for Multiple Object Tracking 106 | - Video Object Segmentation with Re-identification 107 | - Online Adaptation of Convolutional Neural Networks for Video Object Segmentation 108 | - Learning to Segment Instances in Videos with Spatial Propagation Network 109 | - Efficient Video Object Segmentation via Network Modulation 110 | 111 | #### weakly segmentation 112 | - Weakly- and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation 113 | - BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation 114 | - Constrained Convolutional Neural Networks for Weakly Supervised Segmentation 115 | - Augmented Feedback in Semantic Segmentation under Image Level Supervision 116 | - Webly Supervised Semantic Segmentation 117 | - Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach 118 | - Exploiting Saliency for Object Segmentation from Image Level Labels 119 | - Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation 120 | 121 | #### saliency 122 | - A Model of Saliency-based Visual Attention for Rapid Scene Analysis [[paper]](https://pdfs.semanticscholar.org/e5ae/9c2093699913a480bc0b25c3cd3b958a6b18.pdf) 123 | - Saliency Detection: A Spectral Residual Approach 124 | - Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images(**eDN**) 125 | - SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks 126 | - SALICON: Saliency in Context Ming 127 | - Recurrent Attentional Networks for Saliency Detection 128 | - DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection 129 | - Deeply supervised salient object detection with short connections 130 | - What do different evaluation metrics tell us about saliency models? 131 | - Deep Level Sets for Salient Object Detection Ping 132 | - Non-Local Deep Features for Salient Object Detection 133 | - A Stagewise Refinement Model for Detecting Salient Objects in Images 134 | - Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection 135 | - Deep Contrast Learning for Salient Object Detection 136 | - Instance-Level Salient Object Segmentation 137 | - S4Net: Single Stage Salient-Instance Segmentation 138 | - Salient Object Detection: A Survey 139 | - Salient Object Detection: A Benchmark 140 | 141 | ## Datasets 142 | ### Segmentation 143 | - [PASCAL VOC 2012](http://host.robots.ox.ac.uk:8080/pascal/VOC/) 144 | - [Cityscapes](https://www.cityscapes-dataset.com/) 145 | - [MIT ADE 20K](http://groups.csail.mit.edu/vision/datasets/ADE20K/) 146 | - [COCO Stuff](http://cocodataset.org/#stuff-challenge2017) 147 | 148 | ### Saliency 149 | - [MSARA10K](http://mmcheng.net/zh/msra10k/) 150 | - [ECSSD](http://www.cse.cuhk.edu.hk/leojia/projects/hsaliency/dataset.html) 151 | - [SALICON](http://salicon.net/challenge-2017/) 152 | - [DUT-OMRON](http://saliencydetection.net/dut-omron/) 153 | - [DUTS](http://saliencydetection.net/duts/) 154 | 155 | ## Software and Skills 156 | ### Framework 157 | - Keras [[docs]](https://keras.io/) 158 | - Caffe [[install&docs]](http://caffe.berkeleyvision.org/) 159 | - Caffe2 [[install&docs]](http://caffe2.ai/) 160 | - PyTorch [[install]](http://pytorch.org/) [[docs]](http://pytorch.org/docs/0.3.0/) 161 | - Mxnet/Gluon [[install&docs]](http://mxnet.incubator.apache.org/) 162 | - TensorFlow [[install&docs]](https://www.tensorflow.org/) 163 | 164 | ### Skills 165 | - [git](http://rogerdudler.github.io/git-guide/index.zh.html) 166 | - [python tutorial](https://www.liaoxuefeng.com/wiki/001374738125095c955c1e6d8bb493182103fac9270762a000/0013747381369301852037f35874be2b85aa318aad57bda000) 167 | - tmux 168 | - vim 169 | - markdown 170 | - latex 171 | --------------------------------------------------------------------------------