不放过每一个学习的机会，关注微信公众号：AI算法爱好者
或扫描二维码：

说实话，单是CVPR2019就有1300篇文章了，还有ECCV，ICCV，AAAI，ICLR，NeurlPS，BMVC，TPAMI，IJCV，ECML-PKDD，还有预印本的arXiv，是不是光会议就看花了眼？这么多文章是不可能全都看的，这时候就需要挑一些高质量的论文拿出来看看。但是如何找出高质量论文也是一件棘手和费时的问题，不妨看看这些个大佬的总结。

下面这张图来自github 5000多star的项目：deep learning object detection

该项目总结了从2014到2019年各大会议的优秀文章，并将重量级论文标红为必读，当然此处未标红的论文也很重要，可以在时间充足的情况下阅读。

github链接：

https://github.com/hoya012/deep_learning_object_detection

部分论文性能对比

这里给出的是mAP的比较。没有给出FPS的比较，因为每篇论文的作者给出的FPS都是基于不同的硬件，直接对比没有太大意义。

历年经典论文

2014

• [R-CNN] Rich feature hierarchies for accurate object detection and semantic segmentation | [CVPR’ 14] |[pdf] [official code - caffe]

• [OverFeat] OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks | [ICLR’ 14] |[pdf] [official code - torch]

• [MultiBox] Scalable Object Detection using Deep Neural Networks | [CVPR’ 14] |[pdf]

• [SPP-Net] Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition | [ECCV’ 14] |[pdf] [official code - caffe] [unofficial code - keras] [unofficial code - tensorflow]

2015

• Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction | [CVPR’ 15] |[pdf] [official code - matlab]

• [MR-CNN] Object detection via a multi-region & semantic segmentation-aware CNN model | [ICCV’ 15] |[pdf] [official code - caffe]

• [DeepBox] DeepBox: Learning Objectness with Convolutional Networks | [ICCV’ 15] |[pdf] [official code - caffe]

• [AttentionNet] AttentionNet: Aggregating Weak Directions for Accurate Object Detection | [ICCV’ 15] |[pdf]

• [Fast R-CNN] Fast R-CNN | [ICCV’ 15] |[pdf] [official code - caffe]

• [DeepProposal] DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers | [ICCV’ 15] |[pdf] [official code - matconvnet]

• [Faster R-CNN, RPN] Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks | [NIPS’ 15] |[pdf] [official code - caffe] [unofficial code - tensorflow] [unofficial code - pytorch]

2016

• [YOLO v1] You Only Look Once: Unified, Real-Time Object Detection | [CVPR’ 16] |[pdf] [official code - c]

• [G-CNN] G-CNN: an Iterative Grid Based Object Detector | [CVPR’ 16] |[pdf]

• [AZNet] Adaptive Object Detection Using Adjacency and Zoom Prediction | [CVPR’ 16] |[pdf]

• [ION] Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks | [CVPR’ 16] |[pdf]

• [HyperNet] HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection | [CVPR’ 16] |[pdf]

• [OHEM] Training Region-based Object Detectors with Online Hard Example Mining | [CVPR’ 16] |[pdf] [official code - caffe]

• [CRAPF] CRAFT Objects from Images | [CVPR’ 16] |[pdf] [official code - caffe]

• [MPN] A MultiPath Network for Object Detection | [BMVC’ 16] |[pdf] [official code - torch]

• [SSD] SSD: Single Shot MultiBox Detector | [ECCV’ 16] |[pdf] [official code - caffe] [unofficial code - tensorflow] [unofficial code - pytorch]

• [GBDNet] Crafting GBD-Net for Object Detection | [ECCV’ 16] |[pdf] [official code - caffe]

• [CPF] Contextual Priming and Feedback for Faster R-CNN | [ECCV’ 16] |[pdf]

• [MS-CNN] A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection | [ECCV’ 16] |[pdf] [official code - caffe]

• [R-FCN] R-FCN: Object Detection via Region-based Fully Convolutional Networks | [NIPS’ 16] |[pdf] [official code - caffe] [unofficial code - caffe]

• [PVANET] PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection | [NIPSW’ 16] |[pdf] [official code - caffe]

• [DeepID-Net] DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection | [PAMI’ 16] |[pdf]

• [NoC] Object Detection Networks on Convolutional Feature Maps | [TPAMI’ 16] |[pdf]

2017

• [DSSD] DSSD : Deconvolutional Single Shot Detector | [arXiv’ 17] |[pdf] [official code - caffe]

• [TDM] Beyond Skip Connections: Top-Down Modulation for Object Detection | [CVPR’ 17] |[pdf]

• [FPN] Feature Pyramid Networks for Object Detection | [CVPR’ 17] |[pdf] [unofficial code - caffe]

• [YOLO v2] YOLO9000: Better, Faster, Stronger | [CVPR’ 17] |[pdf] [official code - c] [unofficial code - caffe] [unofficial code - tensorflow] [unofficial code - tensorflow] [unofficial code - pytorch]

• [RON] RON: Reverse Connection with Objectness Prior Networks for Object Detection | [CVPR’ 17] |[pdf] [official code - caffe] [unofficial code - tensorflow]

• [RSA] Recurrent Scale Approximation for Object Detection in CNN | | [ICCV’ 17] |[pdf] [official code - caffe]

• [DCN] Deformable Convolutional Networks | [ICCV’ 17] |[pdf] [official code - mxnet] [unofficial code - tensorflow] [unofficial code - pytorch]

• [DeNet] DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling | [ICCV’ 17] |[pdf] [official code - theano]

• [CoupleNet] CoupleNet: Coupling Global Structure with Local Parts for Object Detection | [ICCV’ 17] |[pdf] [official code - caffe]

• [RetinaNet] Focal Loss for Dense Object Detection | [ICCV’ 17] |[pdf] [official code - keras] [unofficial code - pytorch] [unofficial code - mxnet] [unofficial code - tensorflow]

• [Mask R-CNN] Mask R-CNN | [ICCV’ 17] |[pdf] [official code - caffe2] [unofficial code - tensorflow] [unofficial code - tensorflow] [unofficial code - pytorch]

• [DSOD] DSOD: Learning Deeply Supervised Object Detectors from Scratch | [ICCV’ 17] |[pdf] [official code - caffe] [unofficial code - pytorch]

• [SMN] Spatial Memory for Context Reasoning in Object Detection | [ICCV’ 17] |[pdf]

• [Light-Head R-CNN] Light-Head R-CNN: In Defense of Two-Stage Object Detector | [arXiv’ 17] |[pdf] [official code - tensorflow]

• [Soft-NMS] Improving Object Detection With One Line of Code | [ICCV’ 17] |[pdf] [official code - caffe]

2018

• [YOLO v3] YOLOv3: An Incremental Improvement | [arXiv’ 18] |[pdf] [official code - c] [unofficial code - pytorch] [unofficial code - pytorch] [unofficial code - keras] [unofficial code - tensorflow]

• [ZIP] Zoom Out-and-In Network with Recursive Training for Object Proposal | [IJCV’ 18] |[pdf] [official code - caffe]

• [SIN] Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships | [CVPR’ 18] |[pdf] [official code - tensorflow]

• [STDN] Scale-Transferrable Object Detection | [CVPR’ 18] |[pdf]

• [RefineDet] Single-Shot Refinement Neural Network for Object Detection | [CVPR’ 18] |[pdf] [official code - caffe] [unofficial code - chainer] [unofficial code - pytorch]

• [MegDet] MegDet: A Large Mini-Batch Object Detector | [CVPR’ 18] |[pdf]

• [DA Faster R-CNN] Domain Adaptive Faster R-CNN for Object Detection in the Wild | [CVPR’ 18] |[pdf] [official code - caffe]

• [SNIP] An Analysis of Scale Invariance in Object Detection – SNIP | [CVPR’ 18] |[pdf]

• [Relation-Network] Relation Networks for Object Detection | [CVPR’ 18] |[pdf] [official code - mxnet]

• [Cascade R-CNN] Cascade R-CNN: Delving into High Quality Object Detection | [CVPR’ 18] |[pdf] [official code - caffe]

• Finding Tiny Faces in the Wild with Generative Adversarial Network | [CVPR’ 18] |[pdf]

• [MLKP] Multi-scale Location-aware Kernel Representation for Object Detection | [CVPR’ 18] |[pdf] [official code - caffe]

• Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation | [CVPR’ 18] |[pdf] [official code - chainer]

• [Fitness NMS] Improving Object Localization with Fitness NMS and Bounded IoU Loss | [CVPR’ 18] |[pdf]

• [STDnet] STDnet: A ConvNet for Small Target Detection | [BMVC’ 18] |[pdf]

• [RFBNet] Receptive Field Block Net for Accurate and Fast Object Detection | [ECCV’ 18] |[pdf] [official code - pytorch]

• Zero-Annotation Object Detection with Web Knowledge Transfer | [ECCV’ 18] |[pdf]

• [CornerNet] CornerNet: Detecting Objects as Paired Keypoints | [ECCV’ 18] |[pdf] [official code - pytorch]

• [PFPNet] Parallel Feature Pyramid Network for Object Detection | [ECCV’ 18] |[pdf]

• [Softer-NMS] Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection | [arXiv’ 18] |[pdf]

• [ShapeShifter] ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector | [ECML-PKDD’ 18] |[pdf] [official code - tensorflow]

• [Pelee] Pelee: A Real-Time Object Detection System on Mobile Devices | [NIPS’ 18] |[pdf] [official code - caffe]

• [HKRM] Hybrid Knowledge Routed Modules for Large-scale Object Detection | [NIPS’ 18] |[pdf]

• [MetaAnchor] MetaAnchor: Learning to Detect Objects with Customized Anchors | [NIPS’ 18] |[pdf]

• [SNIPER] SNIPER: Efficient Multi-Scale Training | [NIPS’ 18] |[pdf]

2019

• [M2Det] M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network | [AAAI’ 19] |[pdf] [official code - pytorch]

• [R-DAD] Object Detection based on Region Decomposition and Assembly | [AAAI’ 19] |[pdf]

• [CAMOU] CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild | [ICLR’ 19] |[pdf]

• Feature Intertwiner for Object Detection | [ICLR’ 19] |[pdf]

• [GIoU] Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression | [CVPR’ 19] |[pdf]

• Automatic adaptation of object detectors to new domains using self-training | [CVPR’ 19] |[pdf]

• [Libra R-CNN] Libra R-CNN: Balanced Learning for Object Detection | [CVPR’ 19] |[pdf]

• Feature Selective Anchor-Free Module for Single-Shot Object Detection | [CVPR’ 19] |[pdf]

• [ExtremeNet] Bottom-up Object Detection by Grouping Extreme and Center Points | [CVPR’ 19] |[pdf] | [official code - pytorch]

• [C-MIL] C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
  | [CVPR’ 19] |[pdf] | [official code - torch]

• [ScratchDet] ScratchDet: Training Single-Shot Object Detectors from Scratch | [CVPR’ 19] |[pdf]

• Bounding Box Regression with Uncertainty for Accurate Object Detection | [CVPR’ 19] |[pdf] | [official code - caffe2]

• Activity Driven Weakly Supervised Object Detection | [CVPR’ 19] |[pdf]

• Towards Accurate One-Stage Object Detection with AP-Loss | [CVPR’ 19] |[pdf]

• Strong-Weak Distribution Alignment for Adaptive Object Detection | [CVPR’ 19] |[pdf] | [official code - pytorch]

• [NAS-FPN] NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection | [CVPR’ 19] |[pdf]

• [Adaptive NMS] Adaptive NMS: Refining Pedestrian Detection in a Crowd | [CVPR’ 19] |[pdf]

• Point in, Box out: Beyond Counting Persons in Crowds | [CVPR’ 19] |[pdf]

• Locating Objects Without Bounding Boxes | [CVPR’ 19] |[pdf]

• Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects | [CVPR’ 19] |[pdf]

• Towards Universal Object Detection by Domain Attention | [CVPR’ 19] |[pdf]

• Exploring the Bounds of the Utility of Context for Object Detection | [CVPR’ 19] |[pdf]

• What Object Should I Use? - Task Driven Object Detection | [CVPR’ 19] |[pdf]

• Dissimilarity Coefficient based Weakly Supervised Object Detection | [CVPR’ 19] |[pdf]

• Adapting Object Detectors via Selective Cross-Domain Alignment | [CVPR’ 19] |[pdf]

• Fully Quantized Network for Object Detection | [CVPR’ 19] |[pdf]

• Distilling Object Detectors with Fine-grained Feature Imitation | [CVPR’ 19] |[pdf]

• Multi-task Self-Supervised Object Detection via Recycling of Bounding Box Annotations | [CVPR’ 19] |[pdf]

• [Reasoning-RCNN] Reasoning-RCNN: Unifying Adaptive Global Reasoning into Large-scale Object Detection | [CVPR’ 19] |[pdf]

• Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation | [CVPR’ 19] |[pdf]

• Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors | [CVPR’ 19] |[pdf]

• Spatial-aware Graph Relation Network for Large-scale Object Detection | [CVPR’ 19] |[pdf]

• [MaxpoolNMS] MaxpoolNMS: Getting Rid of NMS Bottlenecks in Two-Stage Object Detectors | [CVPR’ 19] |[pdf]

• You reap what you sow: Generating High Precision Object Proposals for Weakly-supervised Object Detection | [CVPR’ 19] |[pdf]

• Object detection with location-aware deformable convolution and backward attention filtering | [CVPR’ 19] |[pdf]

• Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection | [CVPR’ 19] |[pdf]

参考：

https://github.com/hoya012/deep_learning_object_detection

$- END -$−END−