目標檢測（物體檢測, Object Detection) 專知薈萃

入門學習

1. 圖像目標檢測（Object Detection）原理與實現 （1-6）
   • [http://www.voidcn.com/article/p-xnjyqlkj-ua.html]
   • [http://www.voidcn.com/article/p-ypylfzuk-ua.html]
   • [http://www.voidcn.com/article/p-pfihszbt-ua.html]
   • [http://www.voidcn.com/article/p-hcvjcaqy-ua.html]
   • [http://www.voidcn.com/article/p-kjogyjfz-ua.html]
   • [http://www.voidcn.com/article/p-zqfjjomb-u.html]
2. 目標檢測從入門到精通(1-3)
   • [https://www.cnblogs.com/xiaoboge/p/10544336.html]
   • [https://www.cnblogs.com/xiaoboge/p/10552042.html]
   • [https://www.cnblogs.com/xiaoboge/p/10567869.html]
3. 深度學習500問之目標檢測
   • [https://github.com/scutan90/DeepLearning-500-questions/blob/master/ch08_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B/%E7%AC%AC%E5%85%AB%E7%AB%A0_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B.md]
4. 目標檢測（Object Detection）入門
   • [https://blog.csdn.net/f290131665/article/details/81012556]
   • [https://zhuanlan.zhihu.com/p/34142321]

綜述

1. 地平線黃李超開講：深度學習和物體檢測！

   • [https://www.sohu.com/a/163460329_642762]

2. 對話CVPR2016：目標檢測新進展：

   • [https://zhuanlan.zhihu.com/p/21533724]

3. 基於深度學習的目標檢測技術演進：R-CNN、Fast R-CNN、Faster R-CNN：

   • [http://www.cnblogs.com/skyfsm/p/6806246.html]

4. 基於深度學習的目標檢測研究進展

   • [https://mp.weixin.qq.com/s/RxogMJ86FkQHrzaF4SxFNQ]

5. 講堂幹貨No.1｜山世光－基於深度學習的目標檢測技術進展與展望

   • [https://mp.weixin.qq.com/s/NV2hWofOCractLt45-wI1A]

6. 基於特征共享的高效物體檢測 Faster R-CNN和ResNet的作者任少卿 博士畢業論文 中文

   • [https://pan.baidu.com/s/1gfxTbNl]

7. R-CNN：論文筆記

   • [http://www.cnblogs.com/kingstrong/p/4969472.html], [http://blog.gater.vip/articles/2015/11/02/1478607351098.html]

8. Fast-RCNN:

   • 深度學習物體檢測（三）——FAST-RCNN：
   • [https://www.cnblogs.com/yanshw/p/10767212.html]
   • Fast-RCNN:[https://zhuanlan.zhihu.com/p/24780395]

9. Faster-RCNN:

   • [https://www.cnblogs.com/chaofn/p/9310912.html]

10. FPN:

    • Feature Pyramid Networks for Object Detection 論文筆記：
    • [http://blog.csdn.net/jesse_mx/article/details/54588085]
    • CVPR 2017論文解讀：特征金字塔網絡FPN：
    • [http://www.sohu.com/a/159780794_465975]
    • FPN（feature pyramid networks）算法講解：
    • [http://blog.csdn.net/u014380165/article/details/72890275]

11. R-FCN:

    • 基於區域的全卷積網絡來檢測物體:
    • [http://blog.csdn.net/shadow_guo/article/details/51767036]
    • [譯] 基於R-FCN的物體檢測:
    • [http://www.jianshu.com/p/db1b74770e52]

12. SSD:

    • Single Shot MultiBox Detector論文閱讀：
    • [http://blog.csdn.net/u010167269/article/details/52563573]
    • 【深度學習：目標檢測】RCNN學習筆記(10)：SSD:Single Shot MultiBox Detector：
    • [http://blog.csdn.net/smf0504/article/details/52745070]
    • 翻譯SSD論文(Single Shot MultiBox Detector)，僅作交流：
    • [http://blog.csdn.net/Ai_Smith/article/details/52997456?locationNum=2&fps=1]
    • CNN目標檢測與分割（三）：SSD詳解：
    • [https://blog.csdn.net/a8039974/article/details/77592395]
    • SSD關鍵源碼解析：
    • [https://zhuanlan.zhihu.com/p/25100992]

13. YOLO:

    • YOLO：實時快速目標檢測：
    • [https://zhuanlan.zhihu.com/p/25045711]
    • YOLO詳解: [https://zhuanlan.zhihu.com/p/25236464]
    • YOLO升級版：YOLOv2和YOLO9000解析:
    • [https://zhuanlan.zhihu.com/p/29816334]
    • YOLO升級版：YOLOv2和YOLO9000解析：
    • [https://zhuanlan.zhihu.com/p/29816334]
    • YOLO v2之總結篇（linux+windows）：
    • [http://blog.csdn.net/qq_14845119/article/details/53589282]
    • YOLOv2 論文筆記：
    • [http://blog.csdn.net/jesse_mx/article/details/53925356]
    • 目標檢測網絡之 YOLOv3
    • [https://www.cnblogs.com/makefile/p/YOLOv3.html]

14. DenseBox:餘凱特邀報告：基於密集預測圖的物體檢測技術造就全球領先的ADAS係統

    • [http://mp.weixin.qq.com/s/9Z9mO3DJ7uPuirMAbPkDcw]

15. PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection - [http://www.cnblogs.com/xueyuxiaolang/p/5959442.html]

16. 深度學習論文筆記：DSSD - [https://jacobkong.github.io/blog/2938514597/]

17. DSOD

    • 複旦大學Ph.D沈誌強：用於目標檢測的DSOD模型（ICCV 2017） | 分享總結:
    • [http://www.sohu.com/a/198226907_114877]
    • 目標檢測--DSOD: Learning Deeply Supervised Object Detectors from Scratch：
    • [http://blog.csdn.net/zhangjunhit/article/details/77247695]

18. Focal Loss:

    • Focal Loss:
    • [http://blog.csdn.net/u014380165/article/details/77019084]
    • 讀Focal Loss:
    • [https://zhuanlan.zhihu.com/p/28873248]

19. Soft-NMS:

    • 一行代碼改進NMS:
    • [http://blog.csdn.net/shuzfan/article/details/71036040]

20. OHEM:

    • 論文筆記 OHEM: Training Region-based Object Detectors with Online Hard Example Mining:
    • [http://blog.csdn.net/u012905422/article/details/52760669]

21. Mask-RCNN 2017:

    • Mask-RCNN 2017:
    • [http://blog.csdn.net/inuchiyo_china/article/details/70860939]
    • 目標檢測分割--Mask R-CNN:
    • [http://blog.csdn.net/zhangjunhit/article/details/64920075?locationNum=6&fps=1]
    • 解讀|Facebook 何凱明發大招：Mask R-CNN 狙擊目標實例分割:
    • [http://www.sohu.com/a/130676187_642762]

22. 目標檢測之比較

    • 目標檢測之RCNN，SPP-NET，Fast-RCNN，Faster-RCNN：
    • [http://lanbing510.info/2017/08/24/RCNN-FastRCNN-FasterRCNN.html]
    • RCNN, Fast-RCNN, Faster-RCNN的一些事：
    • [http://closure11.com/rcnn-fast-rcnn-faster-rcnn%E7%9A%84%E4%B8%80%E4%BA%9B%E4%BA%8B/]
    • 機器視覺目標檢測補習貼之R-CNN係列 — R-CNN, Fast R-CNN, Faster R-CNN ， 目標檢測補習貼之YOLO實時檢測, You only look once ：
    • [http://nooverfit.com/wp/]
    • 目標檢測算法：RCNN、YOLO vs DPM：
    • [https://juejin.im/entry/59564e1f6fb9a06b9c7408f9]
    • 如何評價rcnn、fast-rcnn和faster-rcnn這一係列方法？:
    • [https://www.zhihu.com/question/35887527]

23. 視覺目標檢測和識別之過去，現在及可能

    • [https://zhuanlan.zhihu.com/p/27546796]

24. CVPR2019目標檢測方法進展綜述

    • [https://zhuanlan.zhihu.com/p/59398728]

25. 基於深度學習的「目標檢測」算法綜述

    • [https://zhuanlan.zhihu.com/p/33981103]

26. 目標檢測綜述

    • [https://www.cnblogs.com/fydeblog/p/10447875.html]
    • [https://blog.csdn.net/electech6/article/details/95240278]
    • [https://www.jianshu.com/p/8c0e0d19399b]

27. 深度學習目標檢測網絡彙總對比

    • [https://shartoo.github.io/obj_detect_summary/]

28. 從錨點到關鍵點，最新的目標檢測方法發展到哪了

    • [http://blog.itpub.net/29829936/viewspace-2654215/]

29. 從RCNN到SSD，這應該是最全的一份目標檢測算法盤點

    • [http://baijiahao.baidu.com/s?id=1598999301741831102&wfr=spider&for=pc]

30. 目標檢測中的不平衡問題：綜述

    • [https://arxiv.org/abs/1909.00169]

31. 深度學習中用於對象檢測的最新進展

    • [https://arxiv.org/abs/1908.03673]

32. 基於深度學習的對象檢測概述

    • [https://arxiv.org/abs/1907.09408]

33. 目標檢測20年：綜述

• [https://arxiv.org/abs/1905.05055]

34. 深度卷積神經網絡時代目標檢測的最新進展
    • [https://arxiv.org/abs/1809.03193]
35. 用於通用對象檢測的深度學習：綜述
    • [https://arxiv.org/abs/1809.02165]

進階文章

1. Deep Neural Networks for Object Detection （基於DNN的對象檢測）NIPS2013:

   • [http://papers.nips.cc/paper/5207-deep-neural-networks-for-object-detection.pdf]

2. R-CNNRich feature hierarchies for accurate object detection and semantic segmentation:

   • [https://arxiv.org/abs/1311.2524]

3. Fast R-CNN:

   • [http://arxiv.org/abs/1504.08083]

4. Faster R-CNNFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks:

   • [http://arxiv.org/abs/1506.01497]

5. Mask R-CNN

   • [http://arxiv.org/abs/1703.06870]

6. Light-Head R-CNN

   • [https://arxiv.org/abs/1711.07264]

7. Cascade R-CNN

   • [https://arxiv.org/abs/1712.00726]

8. Scalable Object Detection using Deep Neural Networks

   • [http://arxiv.org/abs/1312.2249]

9. Scalable, High-Quality Object Detection

   • [http://arxiv.org/abs/1412.1441]

10. SPP-NetSpatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

    • [http://arxiv.org/abs/1406.4729]

11. DeepID-NetDeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection

    • [https://arxiv.org/abs/1412.5661]

12. Object Detectors Emerge in Deep Scene CNNs

    • [http://arxiv.org/abs/1412.6856]

13. segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection

    • [https://arxiv.org/abs/1502.04275]

14. Object Detection Networks on Convolutional Feature Maps

    • [http://arxiv.org/abs/1504.06066]

15. Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction

    • [http://arxiv.org/abs/1504.03293]

16. DeepBox: Learning Objectness with Convolutional Networks

    • [http://arxiv.org/abs/1504.03293]

17. Object detection via a multi-region & semantic segmentation-aware CNN model

    • [http://arxiv.org/abs/1505.01749]

18. You Only Look Once: Unified, Real-Time Object Detection

    • [http://arxiv.org/abs/1506.02640]

19. YOLOv2 YOLO9000: Better, Faster, Stronger

    • [https://arxiv.org/abs/1612.08242]

20. YOLOv3

    • [https://arxiv.org/abs/1804.02767]

21. YOLT

    • [https://arxiv.org/abs/1805.09512]

22. AttentionNet: Aggregating Weak Directions for Accurate Object Detection

    • [http://arxiv.org/abs/1506.07704]

23. DenseBox: Unifying Landmark Localization with End to End Object Detection

    • [http://arxiv.org/abs/1509.04874]

24. SSD: Single Shot MultiBox Detector

    • [http://arxiv.org/abs/1512.02325]

25. DSSD : Deconvolutional Single Shot Detector

    • [https://arxiv.org/abs/1701.06659]

26. FSSD

    • [https://arxiv.org/abs/1712.00960]

27. ESSD

    • [https://arxiv.org/abs/1801.05918]

28. MDSSD

    • [https://arxiv.org/abs/1805.07009]

29. Pelee

    • [https://arxiv.org/abs/1804.06882]

30. Fire SSD

    • https://arxiv.org/abs/1806.05363

31. G-CNN: an Iterative Grid Based Object Detector

    • [http://arxiv.org/abs/1512.07729]

32. HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection

    • [http://arxiv.org/abs/1604.00600]

33. A MultiPath Network for Object Detection

    • [http://arxiv.org/abs/1604.02135]

34. R-FCN: Object Detection via Region-based Fully Convolutional Networks

    • [http://arxiv.org/abs/1605.06409]

35. A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection

    • [http://arxiv.org/abs/1607.07155]

36. PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection

    • [http://arxiv.org/abs/1608.08021]

37. Feature Pyramid Networks for Object Detection

    • [https://arxiv.org/abs/1612.03144]

38. Learning Chained Deep Features and Classifiers for Cascade in Object Detection

    • [https://arxiv.org/abs/1702.07054]

39. DSOD: Learning Deeply Supervised Object Detectors from Scratch

    • [https://arxiv.org/abs/1708.01241]

40. Focal Loss for Dense Object Detection ICCV 2017 Best student paper award. Facebook AI Research

    • [https://arxiv.org/abs/1708.02002]

41. MegDet

    • [https://arxiv.org/abs/1711.07240]

42. Mask-RCNN 2017 ICCV 2017 Best paper award. Facebook AI Research

    • [http://arxiv.org/abs/1703.06870]

43. RefineNet

    • [https://arxiv.org/abs/1711.06897]

44. DetNet

    • [https://arxiv.org/abs/1804.06215]

45. SSOD

    • [https://arxiv.org/abs/1806.03370]

46. CornerNet

    • [https://arxiv.org/abs/1808.01244]

47. M2Det

    • [https://arxiv.org/abs/1811.04533]

48. 3D Object Detection

    • [https://arxiv.org/abs/1901.08373]
    • [https://arxiv.org/abs/1805.04902]

49. ZSD（Zero-Shot Object Detection）

    • [https://arxiv.org/abs/1803.07113]

50. OSD（One-Shot object Detection）

    • [https://arxiv.org/abs/1904.02317]

51. Weakly Supervised Object Detection

    • [https://arxiv.org/abs/1810.02569]

52. Softer-NMS

    • [https://arxiv.org/abs/1809.08545]

53. NAS-FPN，可實現比Mask-RCNN、FPN、SSD更快更好的目標檢測

    • [https://arxiv.org/abs/1904.07392]
    • [https://www.shangyexinzhi.com/article/details/id-112816/]

54. 多方向目標檢測：水平邊界框上的滑動頂點

    • [https://arxiv.org/abs/1911.09358]

55. SM-NAS：結構到模塊的神經體係結構搜索以進行目標檢測

    • [https://arxiv.org/abs/1911.09929]

56. 基於PSNet和邊框回歸的弱監督目標檢測(WSOD)

    • [https://arxiv.org/abs/1911.11512]

57. 帶有可見IoU和Box Sign預測器的遮擋性行人檢測

    • [https://arxiv.org/abs/1911.11449]

58. CSPNet：可以增強CNN學習能力的新型Backbone

    • [https://arxiv.org/abs/1911.11929]

59. ReBiF：殘差雙融合特征金字塔網絡，用於較精確的Single-shot目標檢測

    • [https://arxiv.org/abs/1911.12051]

60. 目標檢測的性能上界討論

    • [https://arxiv.org/abs/1911.12451]

61. DIoU Loss：更快更好地學習邊界框回歸

    • [https://arxiv.org/abs/1911.08287]

62. CoAE：用於One-Shot目標檢測的共同注意和共同激勵

    • [https://arxiv.org/abs/1911.12529]

63. SAPD：Soft Anchor-Point目標檢測

    • [https://arxiv.org/abs/1911.12448]

64. MMOD：基於混合模型的目標檢測邊界框密度估計

    • [https://arxiv.org/abs/1911.12721]

65. IENet：方向性航空目標檢測的One Stage Anchor Free檢測器

    • [https://arxiv.org/abs/1912.00969]

66. MnasFPN：用於移動設備上目標檢測的延遲感知的金字塔體係結構

    • [https://arxiv.org/abs/1912.01106]

67. IPG-Net：用於目標檢測的圖像金字塔引導網絡

    • [https://arxiv.org/abs/1912.00632]

68. MAL：用於目標檢測的多Anchor學習

    • [https://arxiv.org/abs/1912.02252]

69. ATSS：縮小Anchor-free和Anchor-based的性能差距：通過自適應訓練樣本選擇

    • [https://arxiv.org/abs/1912.02424]

70. Strong-Weak Distribution Alignment for Adaptive Object Detection

    • [https://arxiv.org/abs/1812.04798]

71. PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation

    • [https://arxiv.org/abs/1903.00709]

72. Deep HoughVoting for 3D Object Detection in Point Clouds

    • [https://arxiv.org/abs/1904.09664]

73. Simultaneous multi-view instance detection with learned geometric soft-constraints

    • [https://arxiv.org/abs/1907.10892]

74. Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection

    • [https://arxiv.org/abs/1907.10164]

75. Towards Adversarially Robust Object Detection

    • [https://arxiv.org/abs/1907.10310]

76. Multi-adversarial Faster-RCNN for Unrestricted Object Detection

    • [https://arxiv.org/abs/1907.10343]

77. Selectivity or Invariance: Boundary-aware Salient Object Detection

    • [https://arxiv.org/pdf/1812.10066.pdf]

78. Joint Monocular 3D Detection and Tracking

    • [https://arxiv.org/abs/1811.10742]

79. GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition

    • [https://arxiv.org/abs/1907.09653]

80. ThunderNet: Towards Real-time Generic Object Detection

    • [https://arxiv.org/abs/1903.11752]

81. MemorizingNormality to Detect Anomaly: Memory-augmented Deep Autoencoder (MemAE) forUnsupervised Anomaly Detection

    • [https://arxiv.org/abs/1904.02639]

Tutorial

1. CVPR'17 Tutorial Deep Learning for Objects and Scenes by Kaiming He Ross Girshick
   • [http://deeplearning.csail.mit.edu/]
2. ICCV 2015 Tools for Efficient Object Detection
   • [http://mp7.watson.ibm.com/ICCV2015/ObjectDetectionICCV2015.html]
3. Object Detection
   • [http://class.inrialpes.fr/tutorials/triggs-icvss1.pdf]
4. Image Recognition and Object Detection : Part 1
   • [https://www.learnopencv.com/image-recognition-and-object-detection-part1/]
5. R-CNN for Object Detection
   • [https://courses.cs.washington.edu/courses/cse590v/14au/cse590v_wk1_rcnn.pdf]
6. 史上最詳盡的yolo教程
   • https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects
   • https://www.e-learn.cn/content/qita/2332027
7. Keras-RetinaNet訓練自己的數據詳細教程
   • https://blog.csdn.net/sinat_35512245/article/details/88188365

視頻教程

1. cs231 第11講 Detection and Segmentation
   • PPT ：[http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture11.pdf] 視頻：[https://www.youtube.com/watch?v=nDPWywWRIRo&list=PL3FW7Lu3i5JvHM8ljYj-zLfQRF3EO8sYv]
2. Deep Learning for Instance-level Object Understanding by Ross Girshick.
   • PPT：[http://deeplearning.csail.mit.edu/instance_ross.pdf]
   • 視頻：[https://youtu.be/jHv37mKAhV4?t=2349]
3. (全)深度學習之目標檢測常用算法原理+實踐精講
   • [https://www.bilibili.com/video/av68991919?p=1]
4. 最全的目標檢測原理講解
   • [https://www.bilibili.com/video/av70977633?p=1]
5. 深度學習之分類與目標檢測
   • [https://www.bilibili.com/video/av55200663?p=1]
6. 2019最新基於深度學習的目標檢測原理及實踐教程
   • [https://www.bilibili.com/video/av74399668?p=1]
7. Tensorflow Object Detection Tutorial
   • [https://www.youtube.com/watch?v=wdufj-pjE5c]
   • [https://www.youtube.com/watch?v=NV1g0DYb_vs]
   • [https://www.youtube.com/watch?v=HjiBbChYRDw]
   • [https://www.youtube.com/watch?v=8CRFChU3U-U]

代碼

1. R-CNN

   • [https://github.com/rbgirshick/rcnn]

2. Fast R-CNN:

   • [https://github.com/rbgirshick/fast-rcnn]
   • github("Fast R-CNN in MXNet"):https://github.com/precedenceguo/mx-rcnn
   • github:https://github.com/mahyarnajibi/fast-rcnn-torch
   • github:https://github.com/apple2373/chainer-simple-fast-rnn
   • github:https://github.com/zplizzi/tensorflow-fast-rcnn

3. Faster R-CNN

   • github(official, Matlab):https://github.com/ShaoqingRen/faster_rcnn
   • github:https://github.com/rbgirshick/py-faster-rcnn
   • github:https://github.com/mitmul/chainer-faster-rcnn
   • github:https://github.com/andreaskoepf/faster-rcnn.torch
   • github:https://github.com/ruotianluo/Faster-RCNN-Densecap-torch
   • github:https://github.com/smallcorgi/Faster-RCNN_TF
   • github:https://github.com/CharlesShang/TFFRCNN
   • github(C++ demo):https://github.com/YihangLou/FasterRCNN-Encapsulation-Cplusplus
   • github:https://github.com/yhenon/keras-frcnn

4. SPP-Net

   • [https://github.com/ShaoqingRen/SPP_net]

5. YOLO

   • github:https://github.com/gliese581gg/YOLO_tensorflow
   • github:https://github.com/xingwangsfu/caffe-yolo
   • github:https://github.com/frankzhangrui/Darknet-Yolo
   • github:https://github.com/BriSkyHekun/py-darknet-yolo
   • github:https://github.com/tommy-qichang/yolo.torch
   • github:https://github.com/frischzenger/yolo-windows
   • github:https://github.com/AlexeyAB/yolo-windows
   • github:https://github.com/nilboy/tensorflow-yolo

6. YOLOv2

   • github(Chainer):https://github.com/leetenki/YOLOv2
   • github(Keras):https://github.com/allanzelener/YAD2K
   • github(PyTorch):https://github.com/longcw/yolo2-pytorch
   • github(Tensorflow):https://github.com/hizhangp/yolo_tensorflow
   • github(Windows):https://github.com/AlexeyAB/darknet
   • github:https://github.com/choasUp/caffe-yolo9000
   • github:https://github.com/philipperemy/yolo-9000

7. YOLOv3

   • https://github.com/qqwweee/keras-yolo3
   • https://github.com/marvis/pytorch-yolo3
   • https://github.com/experiencor/keras-yolo3
   • https://github.com/ultralytics/yolov3
   • https://github.com/eriklindernoren/PyTorch-YOLOv3
   • https://github.com/YunYang1994/tensorflow-yolov3
   • https://github.com/SpikeKing/keras-yolo3-detection

8. SSD

   • github:https://github.com/zhreshold/mxnet-ssd
   • github:https://github.com/zhreshold/mxnet-ssd.cpp
   • github:https://github.com/rykov8/ssd_keras
   • github:https://github.com/balancap/SSD-Tensorflow
   • github:https://github.com/amdegroot/ssd.pytorch
   • github(Caffe):https://github.com/chuanqi305/MobileNet-SSD

9. Recurrent Scale Approximation for Object Detection in CNN

   • [https://github.com/sciencefans/RSA-for-object-detection]

10. Mask-RCNN 2017

    • Keras [https://github.com/matterport/Mask_RCNN]
    • TensorFlow [https://github.com/CharlesShang/FastMaskRCNN]
    • Pytorch [https://github.com/felixgwu/mask_rcnn_pytorch]
    • caffe [https://github.com/jasjeetIM/Mask-RCNN]
    • MXNet [https://github.com/TuSimple/mx-maskrcnn]

11. Light-Head R-CNN

    • https://github.com/zengarden/light_head_rcnn
    • https://github.com/terrychenism/Deformable-ConvNets/blob/master/rfcn/symbols/resnet_v1_101_rfcn_light.py#L784

12. Cascade R-CNN

    • https://github.com/zhaoweicai/cascade-rcnn

13. YOLT

    • https://github.com/avanetten/yolt

14. DSSD

    • https://github.com/chengyangfu/caffe/tree/dssd
    • https://github.com/MTCloudVision/mxnet-dssd

15. Pelee

    • https://github.com/Robert-JunWang/Pelee

16. R-FCN

    • https://github.com/daijifeng001/R-FCN
    • https://github.com/msracver/Deformable-ConvNets/tree/master/rfcn
    • https://github.com/Orpine/py-R-FCN
    • https://github.com/PureDiors/pytorch_RFCN
    • https://github.com/bharatsingh430/py-R-FCN-multiGPU
    • https://github.com/xdever/RFCN-tensorflow

17. FPN

    • https://github.com/xiaohaoChen/rrc_detection
    • https://github.com/taokong/RON
    • https://github.com/sciencefans/RSA-for-object-detection

18. DSOD

    • https://github.com/szq0214/DSOD
    • https://github.com/Windaway/DSOD-Tensorflow
    • https://github.com/chenyuntc/dsod.pytorch
    • https://github.com/szq0214/GRP-DSOD

19. RetinaNet

    • https://github.com/fizyr/keras-retinanet
    • https://github.com/yhenon/pytorch-retinanet
    • https://github.com/CasiaFan/tensorflow_retinanet

20. MegDet

    • https://github.com//ruinmessi/RFBNet
    • https://github.com/bharatsingh430/snip
    • https://github.com/liulei01/DRBox
    • https://github.com/szq0214/GRP-DSOD
    • https://github.com/Hwang64/MLKP

21. RefineNet

    • https://github.com/sfzhang15/RefineDet
    • https://github.com/lzx1413/PytorchSSD
    • https://github.com/ddlee96/RefineDet_mxnet
    • https://github.com/MTCloudVision/RefineDet-Mxnet

22. DetNet

    • https://github.com/guoruoqian/DetNet_pytorch
    • https://github.com/tsing-cv/DetNet
    • https://github.com/becauseofAI/DetNet-Keras

23. CornerNet

    • https://github.com/umich-vl/CornerNet

24. M2Det

    • https://github.com/qijiezhao/M2Det

25. 3D Object Detection

    • https://github.com/CPFL/Autoware/tree/feature/cnn_lidar_detection

26. Softer-NMS

    • https://github.com/yihui-he/softer-NMS

領域專家

1. Ross Girshick (rbg 大神)
   • [http://www.rossgirshick.info/]
   • Ross Girshick是Facebook AI Research（FAIR）的研究科學家，致力於計算機視覺和機器學習。於2012年在Pedro Felzenszwalb的指導下獲得了芝加哥大學的計算機科學博士學位。在加入FAIR之前，Ross是Redmond的Microsoft Research研究員和加利福尼亞大學伯克利分校的博士後。興趣包括將自然語言處理與計算機視覺相結合的實例級對象理解和視覺推理挑戰。獲得2017年PAMI青年研究獎，並且以開發基於R-CNN（基於區域的卷積神經網絡）方法進行物體檢測而聞名。2017年，還獲得了ICCV的馬爾獎。
2. Kaiming He, Facebook人工智能實驗室科學家Kaiming He
   • [http://kaiminghe.com/]
   • Facebook AI Research（FAIR）的研究科學家。曾在Microsoft Research Asia（MSRA）工作，在獲得博士學位後於2011年加入FAIR。研究興趣是計算機視覺和深度學習。 獲得2018年PAMI青年研究員獎，CVPR 2009最佳論文獎，CVPR 2016，ICCV 2017，ICCV 2017最佳學生論文獎以及ECCV 2018最佳論文榮譽獎的獲得者。殘差網絡（ResNets）是Google Scholar Metrics 2019 中所有領域引用最多的論文.ResNets的應用還包括語言， 語音和AlphaGo。
3. Shaoqing Ren
   • [http://shaoqingren.com/]
   • 2016年9月與他人共同創立了自動駕駛軟件初創公司Momenta。目前，團隊正在研究創新的計算機視覺解決方案，以使自動駕駛汽車成為現實。 獲得中國科學技術大學和Microsoft Research Asia的聯合博士學位的博士學位。我的上司是孫健博士。於2011年從同一部門獲得了工學學士學位。
4. Jian Sun
   • [http://www.jiansun.org/]
   • 首席科學家， MEGVII Technology研究部常務董事。 在Microsoft Research工作了十三年後，加入MEGVII Technology（也稱為Face ++，於2016年7月）擔任首席科學家和研究總經理。 生於中國西安，秦始皇兵馬俑所在地。他獲得了理學學士，碩士學位和博士學位。分別於1997年，2000年和2003年獲得西安交通大學的博士學位。緊隨其後，他加入了Microsoft Research Asia，一直從事計算機視覺和計算機圖形學領域的工作，尤其對解決基礎研究問題和構建實際的工作係統感興趣。他的主要研究興趣是計算攝影和基於圖像的深度學習。
5. Tsung-Yi Lin
   • [https://vision.cornell.edu/se3/people/tsung-yi-lin/]
   • 於2017年 在Serge Belongie的指導下在康奈爾紐約技術學院獲得博士學位。研究興趣是計算機視覺，尤其是學習用於交叉視圖圖像匹配和對象檢測的視覺表示。目前是Google Brain的研究科學家。
6. Ali Farhadi
   • [https://homes.cs.washington.edu/~ali/]
   • 華盛頓大學計算機科學與工程係的副教授。領導著艾倫人工智能研究所的PRIOR團隊。主要對計算機視覺，機器學習，自然語言和視覺的交集，語義在視覺理解中的作用分析以及視覺推理感興趣。

---

初步版本，水平有限，有錯誤或者不完善的地方，歡迎大家提建議和補充，會一直保持更新，本文為專知內容組原創內容，未經允許不得轉載，如需轉載請發送郵件至fangquanyi@gmail.com或 聯係微信專知小助手（Rancho_Fang）

敬請關注//www.webtourguide.com和關注專知公眾號，獲取第一手AI相關知識

最近更新：2019-12-10