└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # SmallObjectDetectionList 2 | List of the Papers Addressing Vision-based Small Object Detection, links to more than 50 papers are given below.(please cite the paper if you benefit from this repository): 3 | 4 | `````````````````````````````` 5 | ### Submitted 6 | 7 | BibTeX entry: 8 | ``` 9 | @ARTICLE{, 10 | title = {A Survey of the Four Pillars for Small Object Detection: Multi-scale Representation, Contextual Information, Super-resolution, and Region Proposal}, 11 | journal = {IEEE Transactions on Systems, Man and Cybernetics: Systems}, 12 | year = {2020}, 13 | pages = {}, 14 | author = {Chen, Guang and Wang, Haitao and Chen, Kai and Li, Zhijun and Song, Zida and Liu, Yinlong and Chen, Wenkai and Knoll, Alois}, 15 | eprint = {} 16 | } 17 | ``` 18 | 19 | `````````````````````````````` 20 | 21 | ## How to request addition of a paper 22 | If you know of a paper that addresses an Vision-based Small Object Detection problem and is not on this repository, you are welcome to request the addition of that paper by submitting a pull request. In your pull request please briefly state which section of your paper is related to which problem. 23 | 24 | 25 | 26 | # Table of Contents 27 | 1.[Multi-scales representation](#1) 28 | >1.1 [Multiple feature maps fusion](#1.1) 29 | 1.2 [Connection method of different feature maps](#1.2) 30 | 31 | 2.[Contextual information](#2) 32 | 33 | 3.[Super-Resolution](#3) 34 | 35 | 4.[Region-proposal](#4) 36 | 37 | 5.[Others](#5) 38 | >5.1 [Traffic road object detection](#5.1) 39 | 5.2 [Others](#5.2) 40 | 41 | 6.[Datasets](#6) 42 | >6.1 [Datasets for traffic road scene](#6.1) 43 | 6.2 [Datasets for generic small objects](#6.2) 44 | 6.3 [Datasets for single category](#6.3) 45 | # 1. Multi-scales representation 46 | 47 | ## 1.1. Multiple feature maps fusion 48 | - MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects, arXiv 2018, [[paper]](https://arxiv.org/pdf/1805.07009.pdf) 49 | - MR-CNN: A Multi-Scale Region-Based Convolutional Neural Network for Small Traffic Sign Recognition, IEEE Acess 2019, [[paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8701699) 50 | - Improving Tiny Vehicle Detection in Complex Scenes, IEEE ICME 2018, [[paper]](https://www.computer.org/csdl/proceedings-article/icme/2018/08486507/14jQfPe2Vca) 51 | - Small Object Detection with Multiscale Features, Int. J. Digit. Multimedia Broadcast 2018, [[paper]](https://pdfs.semanticscholar.org/942e/386250587fc789d807093cc56f0a95f9798c.pdf?_ga=2.175036386.1996274586.1568206454-1908503646.1568206454) 52 | - A detection method for low-pixel ratio object, Multimed Tools Appl 2019, [[paper]](https://link.springer.com/content/pdf/10.1007%2Fs11042-018-6653-6.pdf) 53 | - Research on Small Size Object Detection in Complex Background, CAC 2018, [[paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8623078) 54 | - Small Object Detection Using Deep Feature Pyramid Networks, PCM 2018, [[paper]](https://link.springer.com/chapter/10.1007/978-3-030-00764-5_51) 55 | - Multiple receptive fields and small-object-focusing weaklysupervised segmentation network for fast object detection, arXiv 2019, [[paper]](https://arxiv.org/ftp/arxiv/papers/1904/1904.12619.pdf) 56 | - A Block Object Detection Method Based on Feature Fusion Networks for Autonomous Vehicles, Complexity 2019, [[paper]](http://downloads.hindawi.com/journals/complexity/2019/4042624.pdf) 57 | - Small Object Sensitive Segmentation of Urban Street Scene with Spatial Adjacency Between Object Classes, IEEE TIP 2019, [[paper]](https://cse.sc.edu/~songwang/document/tip19b.pdf) 58 | - Small traffic sign detection from large image, Springer Applied Intelligence 2019, [[paper]](https://link.springer.com/article/10.1007%2Fs10489-019-01511-7) 59 | ## 1.2. Connection method of different feature maps 60 | - Detecting Small Objects Using a Channel-Aware Deconvolutional Network, IEEE TCSVT 2019, [[paper]](https://ieeexplore.ieee.org/document/8669953) 61 | - A unified multi-scale deep convolutional neural network for fast object detection, ECCV 2016, [[paper]](http://www.cvlibs.net/projects/autonomous_vision_survey/literature/Cai2016ECCV.pdf) 62 | 63 | # 2. Contextual Information 64 | - Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks, CVPR 2016, [[paper]](http://openaccess.thecvf.com/content_cvpr_2016/papers/Bell_Inside-Outside_Net_Detecting_CVPR_2016_paper.pdf) 65 | - VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection, IEEE TIP 2019, [[paper]](https://arxiv.org/pdf/1905.01583.pdf) 66 | - R-CNN for Small Object Detection, ACCV 2016, [[paper]](https://merl.com/publications/docs/TR2016-144.pdf) 67 | - Detecting The Objects on The Road Using Modular Lightweight Network, arXiv 2019, [[paper]](https://arxiv.org/ftp/arxiv/papers/1811/1811.06641.pdf) 68 | - Feature-fused ssd: fast detection for small objects, ICGIP 2017, [[paper]](https://arxiv.org/ftp/arxiv/papers/1709/1709.05054.pdf) [[code]](https://github.com/wnzhyee/Feature-Fused-SSD) 69 | - Spatial Memory for Context Reasoning in Object Detection, ICCV 2017, [[paper]](http://openaccess.thecvf.com/content_ICCV_2017/papers/Chen_Spatial_Memory_for_ICCV_2017_paper.pdf) 70 | - P-CNN: Part-Based Convolutional Neural Networks for Fine-Grained Visual Categorization, IEEE TPAMI 2019, [[paper]](https://ieeexplore.ieee.org/abstract/document/8789527) 71 | - ContextAware Single-Shot Detector, WACV 2018, [[paper]](https://arxiv.org/pdf/1707.08682.pdf) 72 | - Detecting Traffic Lights by Single Shot Detection, ITSC 2018, [[paper]](https://arxiv.org/pdf/1805.02523.pdf) [[code]](https://github.com/julimueller/tl_ssd) 73 | - SCAN: Semantic Context Aware Network for Accurate Small Object Detection, IJCIS 2018, [[paper]](https://www.atlantis-press.com/journals/ijcis/25894607/view) 74 | - SINet: A Scale Insensitive Convolutional Neural Network for Fast Vehicle Detection, IEEE ITS 2019, [[paper]](https://arxiv.org/pdf/1804.00433.pdf) 75 | - Robust Obstacle Detection and Recognition for Driver Assistance Systems, IEEE ITS 2019, [[paper]](https://www.researchgate.net/profile/Jiaxu_Leng2/publication/332438373_Robust_Obstacle_Detection_and_Recognition_for_Driver_Assistance_Systems/links/5cbeb092a6fdcc1d49a87438/Robust-Obstacle-Detection-and-Recognition-for-Driver-Assistance-Systems.pdf) 76 | - Small Object Detection Using Context Information Fusion in Faster R-CNN, IEEE ICCC 2018, [[paper]](https://ieeexplore.ieee.org/abstract/document/8780579) 77 | 78 | # 3. Super-Resolution 79 | - JCS-Net: Joint Classification and SuperResolution Network for Small-scale Pedestrian Detection in Surveillance Images, IEEE TIFS 2019, [[paper]](https://ieeexplore.ieee.org/abstract/document/8714071) 80 | - Accurate image super-resolution using very deep convolutional networks, CVPR 2016, [[paper]](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Kim_Accurate_Image_Super-Resolution_CVPR_2016_paper.pdf) 81 | - Finding tiny faces in the wild with generative adversarial network, CVPR 2018, [[paper]](http://openaccess.thecvf.com/content_cvpr_2018/papers/Bai_Finding_Tiny_Faces_CVPR_2018_paper.pdf) 82 | - Multi-branch fully convolutional network for face detection, arXiv 2017, [[paper]](https://arxiv.org/pdf/1707.06330.pdf) 83 | - SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network, ECCV 2018, [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/papers/Yongqiang_Zhang_SOD-MTGAN_Small_Object_ECCV_2018_paper.pdf) 84 | - Improving Small Object Detection, ACPR 2017, [[paper]](http://cdn.iiit.ac.in/cdn/cvit.iiit.ac.in/images/ConferencePapers/2017/Improving-SmallObject-Detection.pdf) 85 | - Perceptual Generative Adversarial Networks for Small Object Detection, CVPR 2017, [[paper]](http://openaccess.thecvf.com/content_cvpr_2017/papers/Li_Perceptual_Generative_Adversarial_CVPR_2017_paper.pdf) 86 | - Prior Knowledge Guided Small Object Detection on High-Resolution Images, IEEE ICIP 2019, [[paper]](https://ieeexplore.ieee.org/abstract/document/8802612) 87 | 88 | # 4. Region-Proposal 89 | - AttentionMask: Attentive, Efficient Object Proposal Generation Focusing on Small Objects, ACCV 2018, [[paper]](https://arxiv.org/pdf/1811.08728.pdf) [[code]](https://github.com/chwilms/AttentionMask) 90 | - A PSO and BFO-Based Learning Strategy Applied to Faster R-CNN for Object Detection in Autonomous Driving, IEEE Access 2019, [[paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8633817) 91 | - Improving Small Object Proposals for Company Logo Detection, ICMR 2017, [[paper]](https://arxiv.org/pdf/1704.08881.pdf) 92 | - Augmentation for small object detection, arXiv 2019, [[paper]](https://arxiv.org/pdf/1902.07296) 93 | - Detecting Small Signs from Large Images, IEEE IRI 2017, [[paper]](https://arxiv.org/pdf/1706.08574.pdf) 94 | - Cascade Mask Generation Framework for Fast Small Object Detection, IEEE ICME 2018, [[paper]](https://ieeexplore.ieee.org/abstract/document/8486561) 95 | - Cascaded CNN Method for Far Object Detection in Outdoor Surveillance, IEEE SITIS 2018, [[paper]](https://ieeexplore.ieee.org/abstract/document/8706233) 96 | - SSD-MSN: An Improved Multi-scale Object Detection Network Based on SSD, IEEE Access 2019, [[paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8736726) 97 | - Efficient Small Object Detection with an Improved Region Proposal Networks, IOP Conf. Ser.: Mater. Sci. Eng. 2019, [[paper]](https://iopscience.iop.org/article/10.1088/1757-899X/533/1/012062) 98 | 99 | # 5. Others 100 | 101 | ## 5.1. Traffic road object detection 102 | - Knowledge-based recurrent attentive neural network for small object detection, arXiv 2018, [[paper]](https://arxiv.org/pdf/1803.05263.pdf) 103 | - Efficient convNets for fast traffic sign recognition, IET ITS 2019, [[paper]](https://digital-library.theiet.org/content/journals/10.1049/iet-its.2018.5489) 104 | - Real-time small traffic sign detection with revised faster-RCNN, Multimed Tools Appl 2019, [[paper]](https://link.springer.com/article/10.1007/s11042-018-6428-0) 105 | - Small-scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation, ECCV 2018, [[paper]](http://openaccess.thecvf.com/content_ECCV_2018/papers/Tao_Song_Small-scale_Pedestrian_Detection_ECCV_2018_paper.pdf) 106 | - An Efficient Color Space for Deep-Learning Based Traffic Light Recognition, J Adv Transport 2018, [[paper]](http://downloads.hindawi.com/journals/jat/2018/2365414.pdf) 107 | - CFENet: An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving, arXiv 2018, [[paper]](https://arxiv.org/pdf/1806.09790.pdf) 108 | - Research on Vehicle Object Detection Method Based on Convolutional Neural Network, IEEE ISCID 2018, [[paper]](https://ieeexplore.ieee.org/abstract/document/8695461) 109 | - An Improved Faster R-CNN for Small Object Detection, IEEE Access 2019, [[paper]](https://ieeexplore.ieee.org/document/8786135/authors#authors) 110 | - Detecting Small Objects in Urban Settings Using SlimNet Model, IEEE TGRS 2019, [[paper]](https://ieeexplore.ieee.org/abstract/document/8746784) 111 | - Smaller Object Detection for Real-Time Embedded Traffic Flow Estimation Using Fish-Eye Cameras, IEEE ICIP 2019, [[paper]](https://ieeexplore.ieee.org/abstract/document/8803719) 112 | 113 | ## 5.2. others 114 | - An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection, CVPR 2019, [[paper]](http://openaccess.thecvf.com/content_CVPRW_2019/papers/CEFRL/Lee_An_Energy_and_GPU-Computation_Efficient_Backbone_Network_for_Real-Time_Object_CVPRW_2019_paper.pdf) 115 | - Evaluation of Deep Models for Real-Time Small Object Detection, ICONIP 2017, [[paper]](https://link.springer.com/chapter/10.1007/978-3-319-70090-8_53) 116 | - Small-objectness sensitive detection based on shifted single shot detector, Multimed Tools Appl 2019, [[paper]](https://link.springer.com/article/10.1007/s11042-018-6227-7) 117 | - CNN-based small object detection and visualization with feature activation mapping, IEEE IVCNZ 2017, [[paper]](https://ieeexplore.ieee.org/abstract/document/8402455) 118 | - Real-Time Detecting Method of Marine Small Object with Underwater Robot Vision, IEEE OTO 2018, [[paper]](https://ieeexplore.ieee.org/abstract/document/8558804) 119 | 120 | # 6. Datasets 121 | 122 | ## 6.1. Datasets for traffic road scene 123 | - Lost and Found, [[paper]](https://arxiv.org/pdf/1609.04653.pdf) 124 | - Swedish Traffic Signs, [[paper]](https://link.springer.com/content/pdf/10.1007/978-3-642-21227-7_23.pdf) 125 | - Tsinghua-Tencent 100 K, [[paper]](http://openaccess.thecvf.com/content_cvpr_2016/papers/Zhu_Traffic-Sign_Detection_and_CVPR_2016_paper.pdf) 126 | - GTSDB, [[paper]](https://ieeexplore.ieee.org/abstract/document/6706807) 127 | - CURE-TSD, [[paper]](https://arxiv.org/abs/1902.06857) 128 | 129 | ## 6.1. Datasets for generic small objects 130 | - Small Object Dataset, [[paper]](https://merl.com/publications/docs/TR2016-144.pdf) 131 | - CURE-OR, [[paper]](https://ieeexplore.ieee.org/abstract/document/8614053) 132 | 133 | ## 6.3. Datasets for single category 134 | - WIDER FACE, [[paper]](http://openaccess.thecvf.com/content_cvpr_2016/papers/Yang_WIDER_FACE_A_CVPR_2016_paper.pdf) 135 | - DeepScores, [[paper]](https://arxiv.org/pdf/1804.00525.pdf) 136 | 137 | 138 | 139 | # Contact 140 | Please contact Guang Chen (email:tj_autodrive@hotmail.com) | Zida Song(email:szd16688@qq.com) for your questions about this webpage. 141 | --------------------------------------------------------------------------------