目标檢測（Object Detection）是深度學習 CV 領域的一個核心研究領域和重要分支。縱觀 2013 年到 2019 年，從最早的 R-CNN、Fast R-CNN 到後來的 YOLO v2、YOLO v3 再到今年的 M2Det，新模型層出不窮，性能也越來越好！本文将會對目标檢測近幾年的發展和相關論文做出一份系統介紹，總結一份超全的文獻 paper 清單。
模型清單先一睹為快！（建議收藏）
模型性能比較
FPS（速度）索引與硬體規格（如 CPU、GPU、RAM 等）有關，是以很難進行同等比較。解決方案是在具有相同規格的硬體上測量所有模型的性能，但這是非常困難和耗時的。比較結果如下：
、
下面舉例對标紅的重要模型進行介紹！
2014 年
R-CNN
Rich feature hierarchies for accurate object detection and semantic segmentation | Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik | [CVPR' 14]
論文：
https://arxiv.org/pdf/1311.2524.pdf代碼 Caffe：
https://github.com/rbgirshick/rcnnOverFeat
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks | Pierre Sermanet, et al. | [ICLR' 14]
https://arxiv.org/pdf/1312.6229.pdf代碼 Torch：
https://github.com/sermanet/OverFeat2015 年
Fast R-CNN
Fast R-CNN | Ross Girshick | [ICCV' 15]
https://arxiv.org/pdf/1504.08083.pdf代碼 caffe：
https://github.com/rbgirshick/fast-rcnnFaster R-CNN
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks | Shaoqing Ren, et al. | [NIPS' 15]
https://papers.nips.cc/paper/5638-faster-r-cnn-towards-real-time-object-detection-with-region-proposal-networks.pdf https://github.com/rbgirshick/py-faster-rcnn代碼 tensorflow：
https://github.com/endernewton/tf-faster-rcnn代碼 pytorch：
https://github.com/jwyang/faster-rcnn.pytorch2016 年
OHEM
Training Region-based Object Detectors with Online Hard Example Mining | Abhinav Shrivastava, et al. | [CVPR' 16]
https://arxiv.org/pdf/1604.03540.pdf https://github.com/abhi2610/ohemYOLO v1
You Only Look Once: Unified, Real-Time Object Detection | Joseph Redmon, et al. | [CVPR' 16]
https://arxiv.org/pdf/1506.02640.pdf代碼 c：
https://pjreddie.com/darknet/yolo/SSD
Single Shot MultiBox Detector | Wei Liu, et al. | [ECCV' 16]
https://arxiv.org/pdf/1512.02325.pdf https://github.com/weiliu89/caffe/tree/ssd https://github.com/balancap/SSD-Tensorflow https://github.com/amdegroot/ssd.pytorchR-FCN
Object Detection via Region-based Fully Convolutional Networks | Jifeng Dai, et al. | [NIPS' 16]
https://arxiv.org/pdf/1605.06409.pdf https://github.com/daijifeng001/R-FCN https://github.com/YuwenXiong/py-R-FCN2017 年
YOLO v2
Better, Faster, Stronger | Joseph Redmon, Ali Farhadi | [CVPR' 17]
https://arxiv.org/pdf/1612.08242.pdf https://github.com/quhezheng/caffe_yolo_v2 https://github.com/nilboy/tensorflow-yolo https://github.com/sualab/object-detection-yolov2 https://github.com/longcw/yolo2-pytorchFPN
Feature Pyramid Networks for Object Detection | Tsung-Yi Lin, et al. | [CVPR' 17]
http://openaccess.thecvf.com/content_cvpr_2017/papers/Lin_Feature_Pyramid_Networks_CVPR_2017_paper.pdf https://github.com/unsky/FPNRetinaNet
Focal Loss for Dense Object Detection | Tsung-Yi Lin, et al. | [ICCV' 17]
https://arxiv.org/pdf/1708.02002.pdf代碼 keras：
https://github.com/fizyr/keras-retinanet https://github.com/kuangliu/pytorch-retinanet代碼 mxnet：
https://github.com/unsky/RetinaNet https://github.com/tensorflow/tpu/tree/master/models/official/retinanetMask R-CNN
Kaiming He, et al. | [ICCV' 17]
http://openaccess.thecvf.com/content_ICCV_2017/papers/He_Mask_R-CNN_ICCV_2017_paper.pdf代碼 caffe2：
https://github.com/facebookresearch/Detectron https://github.com/matterport/Mask_RCNN https://github.com/CharlesShang/FastMaskRCNN https://github.com/multimodallearning/pytorch-mask-rcnn2018 年
YOLO v3
An Incremental Improvement | Joseph Redmon, Ali Farhadi | [arXiv' 18]
https://pjreddie.com/media/files/papers/YOLOv3.pdf https://github.com/ayooshkathuria/pytorch-yolo-v3 https://github.com/eriklindernoren/PyTorch-YOLOv3 https://github.com/qqwweee/keras-yolo3 https://github.com/mystic123/tensorflow-yolo-v3RefineDet
Single-Shot Refinement Neural Network for Object Detection | Shifeng Zhang, et al. | [CVPR' 18]
http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Single-Shot_Refinement_Neural_CVPR_2018_paper.pdf https://github.com/sfzhang15/RefineDet代碼 chainer：
https://github.com/fukatani/RefineDet_chainer https://github.com/lzx1413/PytorchSSD2019 年
M2Det
A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network | Qijie Zhao, et al. | [AAAI' 19]
https://arxiv.org/pdf/1811.04533.pdf參考文獻
該項目的參考文獻來自于論文《Deep Learning for Generic Object Detection: A Survey》
論文位址：
https://arxiv.org/pdf/1809.02165v1.pdf