目标检测之CNN系列

「爱情、让人受尽委屈。」 2022-08-23 03:54 215阅读 0赞

排行榜

pascal VOC:http://host.robots.ox.ac.uk:8080/leaderboard/main\_bootstrap.php

coco:http://mscoco.org/dataset/\#detections-leaderboard

kitti:http://www.cvlibs.net/datasets/kitti/eval\_object.php

[Regionlets for Generic Object Detection][]

http://blog.csdn.net/maweifei/article/details/59078077

[目标检测中的mAP是什么含义？][mAP]

[awesome-object-proposals][]

[论文笔记之---Speed and accuracy trade-offs for modern convolutional object detectors][---Speed and accuracy trade-offs for modern convolutional object detectors]

[cs231n学习笔记-CNN-目标检测、定位、分割][cs231n_-CNN-]

[基于深度学习的目标检测][Link 1]

[ILSVRC2016目标检测任务回顾：图像目标检测（DET）][ILSVRC2016_DET]

## overfeat ##

[深度学习（二十）基于Overfeat的图片分类、定位、检测-2014 ICLR][Overfeat_-2014 ICLR]

[使用sklearn-theano来做object detection目标检测 (OverFeat)][sklearn-theano_object detection_ _OverFeat]

[深度学习研究理解:OverFeat:Integrated Recognition, Localization and Detection using Convolutional Networks][OverFeat_Integrated Recognition_ Localization and Detection using Convolutional Networks]

## RCNN ##

[读DL论文心得之RCNN][DL_RCNN]

[rcnn学习笔记:Rich feature hierarchies for accurate object detection and semantic segmentation ][rcnn_Rich feature hierarchies for accurate object detection and semantic segmentation]

[R-CNN论文详解][R-CNN]

## DeepID-Net ##

[DeepID-Net:multi-stage and deformable deep CNNs for object detection][DeepID-Net_multi-stage and deformable deep CNNs for object detection]

## selective search & Edge box ##

[论文提要“Selective Search for Object Recognition” ][Selective Search for Object Recognition]

[《Selective Search for object recognition》阅读笔记][Selective Search for object recognition]

[Selective Search for Object Recognition(阅读)][Selective Search for Object Recognition 1]

[What makes for effective detection proposals?][What makes for effective detection proposals]

[《Edge Boxes: Locating Object Proposals from Edges》读后感~][Edge Boxes_ Locating Object Proposals from Edges]

[Oriented Object Proposals][]

其实·RPN也算一种

## sppnet ##

[SPPNet][]

[论文笔记 《Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition》][_Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition]

[读DL论文心得之SPP ][DL_SPP]

[Spatial Pyramid Pooling in Deep Convolutional --- Spp\_net][Spatial Pyramid Pooling in Deep Convolutional --- Spp_net]

[深度学习笔记（一）空间金字塔池化阅读笔记Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition][Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition]

[SPP pooling layer][]

[深度学习（十九）基于空间金字塔池化的卷积神经网络物体检测-ECCV 2014][-ECCV 2014]

[Spatial pyramid pooling (SPP)-net （空间金字塔池化）笔记][Spatial pyramid pooling _SPP_-net]

## Fast RCNN ##

[【目标检测】Fast RCNN算法详解 ][Fast RCNN]

[读DL论文心得之Fast RCNN][DL_Fast RCNN]

[论文提要"Fast R-CNN"][Fast R-CNN]

[Fast R-CNN  
][Fast R-CNN 1]

[论文笔记 《Fast R-CNN》][_Fast R-CNN]

[深度学习入门（二）Fast R-CNN][Fast R-CNN 1]

[Fast-rcnn Notes ][Fast-rcnn Notes]

[Fast R-CNN笔记][Fast R-CNN 2]

[论文笔记 Fast R-CNN细节][Fast R-CNN 3]

[Fast R-CNN论文详解][Fast R-CNN 4]

## Faster RCNN ##

[【目标检测】Faster RCNN算法详解 ][Faster RCNN]

[论文笔记：Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks][Faster R-CNN_Towards Real-Time Object Detection with Region Proposal Networks]

[Faster R-CNN论文笔记——FR][Faster R-CNN_FR]

[RCNN & SPP-net & Fast-RCNN & Faster-RCNN][RCNN _ SPP-net _ Fast-RCNN _ Faster-RCNN]

[物体检测-从RCNN到YOLO][-_RCNN_YOLO]

[Region Proposal Networks][]

[Faster R-CNN学习笔记][Faster R-CNN]

[Faster rcnn test浮点运算次数（卷积实现过程，Faster rcnn总体结构和参数）][Faster rcnn test_Faster rcnn]

[bounding box regression][]

[Faster R-CNN论文详解][Faster R-CNN 1]  
[feature map计算方法与faster-rcnn中roi映射到feature map的位置计算方法][feature map_faster-rcnn_roi_feature map]  
[Faster R-CNN][Faster R-CNN 2]

[Faster RCNN-generate\_anchors.py][Faster RCNN-generate_anchors.py]

[faster-rcnn 之 RPN网络的结构解析][faster-rcnn _ RPN]

[faster rcnn的特征图到原图区域映射问题][faster rcnn]

[在CNN网络中roi从原图映射到feature map中的计算方法][CNN_roi_feature map]

[针对Faster RCNN具体细节以及源码的解读之RoIPooling层][Faster RCNN_RoIPooling]

[py-faster rcnn中rpn的3x3的滑框用卷积层来定义的是为什么？][py-faster rcnn_rpn_3x3]

[Faster rcnn相关文章研究][Faster rcnn]

[Faster R-CNN论文详解][Faster R-CNN 1]

http://wenku.baidu.com/link?url=11zlcxN9p7d6ydhJHnDCBltkS9HEyLLZ0sBBgdwq7Oa02BsXeKRIBvDWcPVzKMFV8SOBtc9qdhTilohJ55MhUc7Ht7jDUiCh4yhn5xvRUYMiXX2T9lzG2zdYF5PDuFtn

[Region Proposal Network][]

[Single Bounding Box Regression][]

http://blog.csdn.net/qq\_26898461/article/category/6204814

[CTPN: Detecting Text in Natural Image with Connectionist Text Proposal Network][CTPN_ Detecting Text in Natural Image with Connectionist Text Proposal Network]

[\[目标检测\] Faster R-CNN 深入理解 && 改进方法汇总][Faster R-CNN _ _]

## DeepBox ##

[DeepBox: Learning Objectness with Convolutional Networks][DeepBox_ Learning Objectness with Convolutional Networks]

## YOLO ##

[论文阅读笔记：You Only Look Once: Unified, Real-Time Object Detection][You Only Look Once_ Unified_ Real-Time Object Detection]

[You Only Look Once: Unified, Real-Time Object Detection][You Only Look Once_ Unified_ Real-Time Object Detection 1]

[论文阅读：You Only Look Once: Unified, Real-Time Object Detection][You Only Look Once_ Unified_ Real-Time Object Detection 2]

[You Only Look Once: Unified, Real-Time Object Detection][You Only Look Once_ Unified_ Real-Time Object Detection 3]

http://blog.csdn.net/u012235274/article/category/6204386

[幾個關於 ssd 與 yolo 無法理解的地方][ssd _ yolo]

[图解YOLO][YOLO]

[YOLO2][]

[YOLO详解][YOLO 1]

[YOLOv2 论文笔记][YOLOv2]

yolo v2 训练

## DenseBox ##

[DenseBox: Unifying Landmark Localization with End to End Object Detection][DenseBox_ Unifying Landmark Localization with End to End Object Detection]

## SSD ##

[论文阅读：SSD: Single Shot MultiBox Detector][SSD_ Single Shot MultiBox Detector]

http://blog.csdn.net/u012235274/article/category/6366885

[为什么SSD要比YOLO快？][SSD_YOLO]

[ssd:single shot detector中的几个问题][ssd_single shot detector]

[SSD: Single Shot MultiBox Detector][SSD_ Single Shot MultiBox Detector 1]

[基于深度学习的目标检测DET - SSD][DET - SSD]

[SSD][]

[DSSD: Deconvolutional Single Shot Detector 论文笔记][DSSD_ Deconvolutional Single Shot Detector]

## G-CNN ##

[论文笔记 G-CNN: an Iterative Grid Based Object Detector][G-CNN_ an Iterative Grid Based Object Detector]

## MultiPathNet ##

[论文笔记 A MultiPath Network for Object Detection][A MultiPath Network for Object Detection]

https://github.com/facebookresearch/multipathnet

## HyperNet ##

[论文笔记 HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection][HyperNet_ Towards Accurate Region Proposal Generation and Joint Object Detection]

[\[论文阅读\]HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection][HyperNet_ Towards Accurate Region Proposal Generation and Joint Object Detection 1]

[HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection][HyperNet_ Towards Accurate Region Proposal Generation and Joint Object Detection 2]

LocNet

[LocNet: Improving Localization Accuracy for Object Detection][LocNet_ Improving Localization Accuracy for Object Detection]

## OHEM ##

[论文笔记 Bootstrapping Face Detection with Hard Negative Examples][Bootstrapping Face Detection with Hard Negative Examples]

[Training Region-based Object Detectors with Online Hard Example Mining - cvpr 2016 oral][]

[OHEM算法及Caffe代码详解][OHEM_Caffe]

https://github.com/abhi2610/ohem

[OHEM算法的Caffe实现][OHEM_Caffe 1]

## R-FCN ##

[论文笔记 R-FCN: Object Detection via Region-based Fully Convolutional Networks][R-FCN_ Object Detection via Region-based Fully Convolutional Networks]

[R-FCN：基于区域的全卷积网络来检测物体][R-FCN]

[R-FCN][R-FCN 1]

[\[论文阅读\]R-FCN: Object Detection via Region-based Fully Convolutional Networks][R-FCN_ Object Detection via Region-based Fully Convolutional Networks 1]

[R-FCN: Object Detection via Region-based Fully Convolutional Networks][R-FCN_ Object Detection via Region-based Fully Convolutional Networks 2]

[R-FCN: Object Detection via Region-based Fully Convolutional Networks][R-FCN_ Object Detection via Region-based Fully Convolutional Networks 3]

https://github.com/Orpine/py-R-FCN

## MS-CNN ##

[论文笔记 MSCNN：A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection][MSCNN_A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection]

https://github.com/zhaoweicai/mscnn

## PVANET ##

[目标检测--PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection][--PVANET_ Deep but Lightweight Neural Networks for Real-time Object Detection]

[PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection - arxiv 2016.08][PVANET_ Deep but Lightweight Neural Networks for Real-time Object Detection - arxiv 2016.08]

[论文笔记：PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection][PVANET_ Deep but Lightweight Neural Networks for Real-time Object Detection]

## FPN ##

[目标检测--Feature Pyramid Networks for Object Detection][--Feature Pyramid Networks for Object Detection]

[FPN + DSSD 阅读笔记][FPN _ DSSD]

[FPN（feature pyramid networks）算法讲解][FPN_feature pyramid networks]

[Feature Pyramid Networks for Object Detection 论文笔记][Feature Pyramid Networks for Object Detection]

## RRC ##

[目标检测--Accurate Single Stage Detector Using Recurrent Rolling Convolution][--Accurate Single Stage Detector Using Recurrent Rolling Convolution]

[Accurate Single Stage Detector Using Recurrent Ring Convolution][]

## focal loss ##

# focal loss #

[Object Detection方法汇总][Object Detection]

[R-CNN,SPP-NET, Fast-R-CNN,Faster-R-CNN, YOLO, SSD系列深度学习检测方法梳理][R-CNN_SPP-NET_ Fast-R-CNN_Faster-R-CNN_ YOLO_ SSD]

[CVPR2016目标检测之识别效率篇：YOLO, G-CNN, Loc-Net][CVPR2016_YOLO_ G-CNN_ Loc-Net]

[CVPR2016目标检测之识别精度篇：ResNet, ION, HyperNet，R-FCN][CVPR2016_ResNet_ ION_ HyperNet_R-FCN]

[深度学习检测方法梳理][Link 2]

[目标检测论文回顾][Link 3]

[对话CVPR2016：目标检测新进展][CVPR2016]

[基于深度学习的目标检测新作][Link 4]

[【目标识别】深度学习进行目标识别的资源列表][Link 5]

[【深度学习论文笔记】Deep Neural Networks for Object Detection][Deep Neural Networks for Object Detection]

[深度卷积神经网络在目标检测中的进展][Link 6]

[目标检测“DPMs are CNNs”][DPMs are CNNs]

[视频目标检测 - Object Detection from Video Tubelets with Convolutional Neural Networks][- Object Detection from Video Tubelets with Convolutional Neural Networks]

[目标检测“Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and”][Exploit All the Layers_ Fast and Accurate CNN Object Detector with Scale Dependent Pooling and]

[Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling 之再阅读][Exploit All the Layers_ Fast and Accurate CNN Object Detector with Scale Dependent Pooling]

[车辆检测”Learning to Detect Vehicles by Clustering Appearance Patterns“][Learning to Detect Vehicles by Clustering Appearance Patterns]

[Fast detection of multiple objects in traffic scenes with a common detection framework][]

[3D Object Proposals for Accurate Object Class Detection][]

[车辆检测“Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model”][Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model]

[论文提要“Filtered Channel Features for Pedestrian Detection”][Filtered Channel Features for Pedestrian Detection]

[论文提要“Taking a Deeper Look at Pedestrians”][Taking a Deeper Look at Pedestrians]

[论文提要“Pedestrian Detection aided by Deep Learning Semantic Tasks”][Pedestrian Detection aided by Deep Learning Semantic Tasks]

[论文提要“Fast Feature Pyramids for Object Detection”][Fast Feature Pyramids for Object Detection]

[目标检测“Object Detection Using Generalization and Efficiency Balanced Co-occurrence Features”][Object Detection Using Generalization and Efficiency Balanced Co-occurrence Features]

[BING][]

[BING++: A Fast High Quality Object Proposal Generator at 100fps][BING_ A Fast High Quality Object Proposal Generator at 100fps]

[综述：计算机视觉中RNN应用于目标识别][RNN]

http://blog.csdn.net/zhangjunhit/article/category/6647655

Is Faster R-CNN Doing Well for Pedestrian Detection?  
  
论文 Is Faster R-CNN Doing Well for Pedestrian Detection?探讨在行人检测领域Faster R-CNN是否有效，提出了RPN + Boosted Forest分类器。

基于R-CNN的多尺度改进方法概述  
  
  
梳理基于R-CNN的多尺度改进方法，主要思路是提取多个层的feature进行卷积层的特征融合(即skip connections),涉及的方法有MultiPath Network，ION(Inside-Outside Net)，HyperNet，PVANET及MS-CNN。  
  
多尺度R-CNN论文笔记(1): A MultiPath Network for Object Detection  
  
多尺度R-CNN论文笔记(2): Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks  
  
多尺度R-CNN论文笔记(3): HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection  
  
多尺度R-CNN论文笔记(4): PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection  
  
多尺度R-CNN论文笔记(5): A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection  
  
多尺度R-CNN论文笔记(6): Feature Pyramid Networks for Object Detection

[Beyond Skip Connections: Top-Down Modulation for Object Detection阅读笔记][Beyond Skip Connections_ Top-Down Modulation for Object Detection]

无proposal，基于回归的检测算法概述  
  
开创性工作YOLO与后续改进，以及G-CNN，SSD等工作。  
无proposal检测方法(1): You Only Look Once: Unified, Real-Time Object Detection  
  
 无proposal检测方法(2): G-CNN: an Iterative Grid Based Object Detector  
  
无proposal检测方法(3): SSD: Single Shot MultiBox Detector  
  
YOLO9000: Better,Faster,Stronger（YOLO9000：更好，更快，更强）

## 和GAN结合 ##

[目标检测“A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection”][A-Fast-RCNN_ Hard Positive Generation via Adversary for Object Detection]

[A-Fast-RCNN算法的Caffe实现][A-Fast-RCNN_Caffe]

[A-Fast-RCNN 论文笔记][A-Fast-RCNN]

## 弱监督/无监督 ##

[目标定位--Deep Self-Taught Learning for Weakly Supervised Object Localization][--Deep Self-Taught Learning for Weakly Supervised Object Localization]

[Is object localization for free? – Weakly Supervised Object Recognition with Convolutional Neural Networks][Is object localization for free_ _ Weakly Supervised Object Recognition with Convolutional Neural Networks]

Weakly Supervised Deep Detection Networks

Weakly supervised localization of novel objects using appearance transfer

ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization

Weakly Supervised Cascaded Convolutional Networks

[Weakly Supervised Object Localization with Progressive Domain Adaptation][]

https://github.com/jbhuang0604/WSL

[PASCAL VOC数据集分析][PASCAL VOC]

VOC2007中包含9963张标注过的图片， 由train/val/test三部分组成， 共标注出24,640个物体。

VOC2007的test数据label已经公布， 之后的没有公布（只有图片，没有label）。  
对于检测任务，VOC2012的trainval/test包含08-11年的所有对应图片。 trainval有11540张图片共27450个物体。  
对于分割任务， VOC2012的trainval包含07-11年的所有对应图片， test只包含08-11。trainval有 2913张图片共6929个物体。

[Pascal VOC 数据集介绍][Pascal VOC]

[VOC数据集mAP计算][VOC_mAP]

[Faster-R-CNN（Python）.2：COCO数据集annotation内容][Faster-R-CNN_Python_.2_COCO_annotation]

[Bounding Box label code][]

**[Udacity Self-Driving 目标检测数据集简介与使用][Udacity Self-Driving]**

[图片标注工具LabelImg使用教程][LabelImg]

## spp\_net实践 ##

[Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition][Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition 1]

[spp\_net 代码实现过程][spp_net]

[spp\_net 在caffe上的实现][spp_net _caffe]

[用caffe训练一个spp\_net网络][caffe_spp_net]

[spp\_solver][spp_solver]

[spp\_net 分类测试][spp_net 1]

## RCNN实践 ##

[使用gpu(gtx1080) cudnn 5.1下编译faster rcnn][gpu_gtx1080_ cudnn 5.1_faster rcnn]

[FAST RCNN安装配置精华][FAST RCNN]

[fast-rcnn配置运行demo.py（Ubuntu14.04）][fast-rcnn_demo.py_Ubuntu14.04]

[faster-RCNN环境配置（Ｕbuntu14.04）][faster-RCNN_buntu14.04]

[Faster RCNN 训练自己的检测模型][Faster RCNN 1]

[Py-faster-rcnn实现自己的数据train和demo][Py-faster-rcnn_train_demo]

[Faster-RCNN+ZF用自己的数据集训练模型(Python版本)][Faster-RCNN_ZF_Python][  
][Py-faster-rcnn_train_demo]

[Faster-RCNN+VGG用自己的数据集训练模型][Faster-RCNN_VGG]

[将数据集做成VOC2007格式用于Faster-RCNN训练][VOC2007_Faster-RCNN]

[Faster R-CNN的安装、测试经历][Faster R-CNN 3]

[Faster-rcnn 训练陨石坑检测][Faster-rcnn]

[Fast RCNN训练自己的数据集 （2修改读写接口）][Fast RCNN_ _2]

[faster-rcnn安装，训练自己的数据][faster-rcnn]

### [Faster R-CNN的安装、测试经历][Faster R-CNN 3] ###

[浅析py-faster-rcnn中不同版本caffe的安装及其对应不同版本cudnn的解决方案][py-faster-rcnn_caffe_cudnn]

[RCNN系列实验的PASCAL VOC数据集格式设置][RCNN_PASCAL VOC]

[ImageNet和PASCAL VOC图像描述的xml文件的解析、修改和生成][ImageNet_PASCAL VOC_xml]

[python生成VOC2007的xml代码][python_VOC2007_xml]

[制作VOC类型数据集，生成txt，生成lmdb][VOC_txt_lmdb]

[Faster rcnn 安装、训练、测试、调试][Faster rcnn 1]

[搭建faster-rcnn进行目标检测的环境][faster-rcnn 1]

[faster rcnn:assert (boxes\[:, 2\] >= boxes\[:, 0\]).all()分析塈VOC2007 xml坐标定义理解][faster rcnn_assert _boxes_ 2_ _ boxes_ 0_.all_VOC2007 xml]

[解决faster-rcnn中训练时assert（boxes\[:,2\]>=boxes\[:,0\]）.all()的问题][faster-rcnn_assert_boxes_2_boxes_0_.all]

[GTX1080+Cuda8.0+Cudnnv5+caffe+faster-rcnn][GTX1080_Cuda8.0_Cudnnv5_caffe_faster-rcnn]

[py-faster-rcnn支持cuDNN V5的方法][py-faster-rcnn_cuDNN V5]

[faster rcnn +cudnn V5][faster rcnn _cudnn V5]

### [faster rcnn +cudnn V5 不兼容问题的改进][faster rcnn _cudnn V5 1] ###

[faster rcnn demo.py:在一个窗口显示所有类别标注][faster rcnn demo.py]

[TensorFlow 上基于 Faster RCNN 的目标检测][TensorFlow _ Faster RCNN]

http://blog.csdn.net/10km/article/category/6816967

[搭建faster-rcnn进行目标检测的环境][faster-rcnn 1]

[Faster-RCNN训练自己的数据集——备忘][Faster-RCNN]

[Faster RCNN参数详解][Faster RCNN 2]

faster rcnn multi GPU

https://www.google.com/search?sclient=psy-ab&site=&source=hp&btnG=Search&q=faster+rcnn+multi+gpu

https://github.com/rbgirshick/py-faster-rcnn/issues/143

https://github.com/bharatsingh430/py-R-FCN-multiGPU

[Check rpn proposals in faster-rcnn][]

https://github.com/endernewton/tf-faster-rcnn

https://github.com/msracver/Deformable-ConvNets

https://github.com/bharatsingh430/Deformable-ConvNets/

## yolo实践 ##

[yolo-darknet配置安装与测试][yolo-darknet]

[yolo-darknet实现自己数据的train和test][yolo-darknet_train_test]

https://github.com/xingwangsfu/caffe-yolo

[caffe 版本 yolo 过程记录][caffe _ yolo]

[YOLO用自己的数据集训练模型][YOLO 2]

https://pjreddie.com/darknet/yolo/

http://guanghan.info/blog/en/my-works/train-yolo/

[YOLOv2训练自己的数据集（VOC格式）][YOLOv2_VOC]

[yolo训练之样本准备环节][yolo]

[使用YOLO训练自己的数据样本经验总结][YOLO 3]

[yolo训练之训练结果评估环节][yolo 1]

[YOLO下一步：输出预测boundingbox做进一步处理][YOLO_boundingbox]

[yolo模型的批量测试和位置输出][yolo 2]

[yolo的训练和测试][yolo 3]

## SSD实践 ##

[SSD的配置安装与测试][SSD 1]

[SSD train your own data][]

[SSD: Signle Shot Detector 用于自然场景文字检测][SSD_ Signle Shot Detector]

[SSD: Single Shot MultiBox Detector在Linux上的配置及运行][SSD_ Single Shot MultiBox Detector_Linux]

[SSD(Single Shot MultiBox Detector):ubuntu16安装及训练自己的数据集(VOC2007格式)过程记录][SSD_Single Shot MultiBox Detector_ubuntu16_VOC2007]

[SSD框架训练自己的数据集][SSD 2]

[以resnet作为前置网络的ssd目标提取检测][resnet_ssd]

[Single Shot Detection(SSD)bbox prediction相关的（超）参数][Single Shot Detection_SSD_bbox prediction]

[Anchors in SSD][]

[SSD的图片预处理][SSD 3]

[SSD的Matching Strategy][SSD_Matching Strategy]

https://github.com/balancap/SSD-Tensorflow

[ssd.pytorch][]

## pva net ##

[caffe\_pvanet,cuda7.5,VS2013][caffe_pvanet_cuda7.5_VS2013]

### [pva-faster-rcnn配置过程出现的问题(个人笔记)][pva-faster-rcnn] ###

### [自制作数据上的pva faster rcnn 训练][pva faster rcnn] ###

## R-FCN实践 ##

[R-FCN配置（python版）][R-FCN_python]

[R-FCN+ResNet-50用自己的数据集训练模型(python版本)][R-FCN_ResNet-50_python]

[R-FCN、SSD、YOLO2、faster-rcnn和labelImg实验笔记][R-FCN_SSD_YOLO2_faster-rcnn_labelImg]

[Regionlets for Generic Object Detection]: http://blog.csdn.net/autocyz/article/details/44919725
[mAP]: https://www.zhihu.com/question/53405779
[awesome-object-proposals]: https://github.com/caocuong0306/awesome-object-proposals
[---Speed and accuracy trade-offs for modern convolutional object detectors]: http://blog.csdn.net/he_is_all/article/details/56485921
[cs231n_-CNN-]: http://blog.csdn.net/myarrow/article/details/51878004
[Link 1]: http://www.cnblogs.com/gujianhan/p/6035514.html
[ILSVRC2016_DET]: https://www.leiphone.com/news/201701/u3D5QnJbS9khm0VT.html?viewType=weixin
[Overfeat_-2014 ICLR]: http://blog.csdn.net/hjimce/article/details/50187881
[sklearn-theano_object detection_ _OverFeat]: http://blog.csdn.net/taneijia/article/details/46118609
[OverFeat_Integrated Recognition_ Localization and Detection using Convolutional Networks]: http://blog.csdn.net/mao_kun/article/details/50571766
[DL_RCNN]: http://blog.csdn.net/liumaolincycle/article/details/49787101
[rcnn_Rich feature hierarchies for accurate object detection and semantic segmentation]: http://blog.csdn.net/liyaohhh/article/details/50824226
[R-CNN]: http://blog.csdn.net/WoPawn/article/details/52133338
[DeepID-Net_multi-stage and deformable deep CNNs for object detection]: http://blog.csdn.net/cv_family_z/article/details/49588969
[Selective Search for Object Recognition]: http://blog.csdn.net/cv_family_z/article/details/46727519
[Selective Search for object recognition]: http://blog.csdn.net/niaolianjiulin/article/details/52950797
[Selective Search for Object Recognition 1]: http://blog.csdn.net/langb2014/article/details/52575507
[What makes for effective detection proposals]: https://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-computing/research/object-recognition-and-scene-understanding/how-good-are-detection-proposals-really/
[Edge Boxes_ Locating Object Proposals from Edges]: http://blog.csdn.net/wsj998689aa/article/details/39476551
[Oriented Object Proposals]: http://blog.csdn.net/cv_family_z/article/details/50125499
[SPPNet]: http://blog.csdn.net/cv_family_z/article/details/46832845
[_Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition]: http://zhangliliang.com/2014/09/13/paper-note-sppnet/
[DL_SPP]: http://blog.csdn.net/liumaolincycle/article/details/49798343
[Spatial Pyramid Pooling in Deep Convolutional --- Spp_net]: http://blog.csdn.net/meanme/article/details/48157751
[Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition]: http://blog.csdn.net/liyaohhh/article/details/50614380
[SPP pooling layer]: http://blog.csdn.net/yuanchheneducn/article/details/52852571
[-ECCV 2014]: http://blog.csdn.net/hjimce/article/details/50187655
[Spatial pyramid pooling _SPP_-net]: http://blog.csdn.net/xzzppp/article/details/51377731
[Fast RCNN]: http://blog.csdn.net/shenxiaolu1984/article/details/51036677
[DL_Fast RCNN]: http://blog.csdn.net/liumaolincycle/article/details/50203333
[Fast R-CNN]: http://blog.csdn.net/cv_family_z/article/details/46713007
[Fast R-CNN 1]: http://blog.csdn.net/liyaohhh/article/details/50651145
[_Fast R-CNN]: http://zhangliliang.com/2015/05/17/paper-note-fast-rcnn/
[Fast-rcnn Notes]: http://blog.csdn.net/DJforeverL/article/details/50759549
[Fast R-CNN 2]: http://blog.csdn.net/xzzppp/article/details/51377771
[Fast R-CNN 3]: http://blog.csdn.net/u012905422/article/details/52819218
[Fast R-CNN 4]: http://blog.csdn.net/WoPawn/article/details/52463853
[Faster RCNN]: http://blog.csdn.net/shenxiaolu1984/article/details/51152614
[Faster R-CNN_Towards Real-Time Object Detection with Region Proposal Networks]: http://blog.csdn.net/anxiaoxi45/article/details/46522155
[Faster R-CNN_FR]: http://blog.csdn.net/qq_17448289/article/details/52871461
[RCNN _ SPP-net _ Fast-RCNN _ Faster-RCNN]: http://blog.sina.com.cn/s/blog_9ae57c020102vopp.html
[-_RCNN_YOLO]: http://blog.csdn.net/cosmosshadow/article/details/50244715
[Region Proposal Networks]: http://blog.csdn.net/iamzhangzhuping/article/details/49449747
[Faster R-CNN]: http://blog.csdn.net/xzzppp/article/details/51582810
[Faster rcnn test_Faster rcnn]: http://blog.csdn.net/xzzppp/article/details/53317011
[bounding box regression]: http://caffecn.cn/?/question/160
[Faster R-CNN 1]: http://blog.csdn.net/WoPawn/article/details/52223282
[feature map_faster-rcnn_roi_feature map]: http://blog.csdn.net/qq_29133371/article/details/53172994
[Faster R-CNN 2]: https://zhuanlan.zhihu.com/p/24916624
[Faster RCNN-generate_anchors.py]: http://blog.csdn.net/weixin_35653315/article/details/54588074
[faster-rcnn _ RPN]: http://blog.csdn.net/sloanqin/article/details/51545125
[faster rcnn]: http://caffecn.cn/?/question/135&utm_source=tuicool&utm_medium=referral
[CNN_roi_feature map]: http://www.caffecn.cn/?/article/25
[Faster RCNN_RoIPooling]: http://blog.csdn.net/xyy19920105/article/details/50420779
[py-faster rcnn_rpn_3x3]: http://caffecn.cn/?/question/449
[Faster rcnn]: http://blog.csdn.net/xzzppp/article/details/52986513
[Region Proposal Network]: http://blog.csdn.net/weixin_35653315/article/details/54577675
[Single Bounding Box Regression]: http://blog.csdn.net/weixin_35653315/article/details/54571681
[CTPN_ Detecting Text in Natural Image with Connectionist Text Proposal Network]: http://blog.csdn.net/duinodu/article/details/70800073
[Faster R-CNN _ _]: http://blog.csdn.net/z5337209/article/details/72838049
[DeepBox_ Learning Objectness with Convolutional Networks]: http://blog.csdn.net/cv_family_z/article/details/50157759
[You Only Look Once_ Unified_ Real-Time Object Detection]: http://blog.csdn.net/tangwei2014/article/details/50915317
[You Only Look Once_ Unified_ Real-Time Object Detection 1]: http://blog.csdn.net/xyy19920105/article/details/50836479
[You Only Look Once_ Unified_ Real-Time Object Detection 2]: http://blog.csdn.net/u010167269/article/details/52638771
[You Only Look Once_ Unified_ Real-Time Object Detection 3]: http://blog.csdn.net/surgewong/article/details/51864859
[ssd _ yolo]: http://www.caffecn.cn/?/question/752
[YOLO]: https://zhuanlan.zhihu.com/p/24916786
[YOLO2]: https://zhuanlan.zhihu.com/p/25167153
[YOLO 1]: https://zhuanlan.zhihu.com/p/25236464
[YOLOv2]: http://blog.csdn.net/jesse_mx/article/details/53925356
[DenseBox_ Unifying Landmark Localization with End to End Object Detection]: http://blog.csdn.net/cv_family_z/article/details/50172741
[SSD_ Single Shot MultiBox Detector]: http://blog.csdn.net/u010167269/article/details/52563573
[SSD_YOLO]: http://www.caffecn.cn/?/question/499
[ssd_single shot detector]: http://www.caffecn.cn/?/question/626
[SSD_ Single Shot MultiBox Detector 1]: http://blog.csdn.net/surgewong/article/details/51871281
[DET - SSD]: http://blog.csdn.net/mao_feng/article/details/52374239
[SSD]: https://zhuanlan.zhihu.com/p/24954433
[DSSD_ Deconvolutional Single Shot Detector]: http://blog.csdn.net/jesse_mx/article/details/55212179
[G-CNN_ an Iterative Grid Based Object Detector]: http://blog.csdn.net/u012905422/article/details/52664918
[A MultiPath Network for Object Detection]: http://blog.csdn.net/u012905422/article/details/52388177
[HyperNet_ Towards Accurate Region Proposal Generation and Joint Object Detection]: http://blog.csdn.net/u012905422/article/details/52614192
[HyperNet_ Towards Accurate Region Proposal Generation and Joint Object Detection 1]: http://blog.csdn.net/u012361214/article/details/51374012
[HyperNet_ Towards Accurate Region Proposal Generation and Joint Object Detection 2]: http://blog.csdn.net/cv_family_z/article/details/51135025
[LocNet_ Improving Localization Accuracy for Object Detection]: http://blog.csdn.net/cv_family_z/article/details/52047262
[Bootstrapping Face Detection with Hard Negative Examples]: http://blog.csdn.net/u012905422/article/details/52331505
[Training Region-based Object Detectors with Online Hard Example Mining - cvpr 2016 oral]: http://blog.csdn.net/zimenglan_sysu/article/details/51318058
[OHEM_Caffe]: http://blog.csdn.net/u014380165/article/details/73148073
[OHEM_Caffe 1]: http://blog.csdn.net/u014380165/article/details/73196223
[R-FCN_ Object Detection via Region-based Fully Convolutional Networks]: http://blog.csdn.net/u012905422/article/details/53242183
[R-FCN]: http://blog.csdn.net/shadow_guo/article/details/51767036
[R-FCN 1]: http://blog.csdn.net/duinodu/article/details/69790844
[R-FCN_ Object Detection via Region-based Fully Convolutional Networks 1]: http://blog.csdn.net/u012361214/article/details/51507590
[R-FCN_ Object Detection via Region-based Fully Convolutional Networks 2]: http://blog.csdn.net/surgewong/article/details/51873372
[R-FCN_ Object Detection via Region-based Fully Convolutional Networks 3]: http://blog.csdn.net/zijin0802034/article/details/53411041
[MSCNN_A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection]: http://blog.csdn.net/u012905422/article/details/52453819
[--PVANET_ Deep but Lightweight Neural Networks for Real-time Object Detection]: http://blog.csdn.net/cv_family_z/article/details/52438372
[PVANET_ Deep but Lightweight Neural Networks for Real-time Object Detection - arxiv 2016.08]: http://blog.csdn.net/zimenglan_sysu/article/details/52471410
[PVANET_ Deep but Lightweight Neural Networks for Real-time Object Detection]: http://blog.csdn.net/u013059662/article/details/52838756
[--Feature Pyramid Networks for Object Detection]: http://blog.csdn.net/zhangjunhit/article/details/65629974
[FPN _ DSSD]: https://zhuanlan.zhihu.com/p/26743074
[FPN_feature pyramid networks]: http://blog.csdn.net/u014380165/article/details/72890275
[Feature Pyramid Networks for Object Detection]: http://blog.csdn.net/jesse_mx/article/details/54588085
[--Accurate Single Stage Detector Using Recurrent Rolling Convolution]: http://blog.csdn.net/zhangjunhit/article/details/70607040
[Accurate Single Stage Detector Using Recurrent Ring Convolution]: http://blog.csdn.net/hk121/article/details/71969061
[Object Detection]: https://handong1587.github.io/deep_learning/2015/10/09/object-detection.html
[R-CNN_SPP-NET_ Fast-R-CNN_Faster-R-CNN_ YOLO_ SSD]: http://www.cnblogs.com/venus024/p/5717766.html
[CVPR2016_YOLO_ G-CNN_ Loc-Net]: http://www.cnblogs.com/venus024/p/5699633.html
[CVPR2016_ResNet_ ION_ HyperNet_R-FCN]: http://www.cnblogs.com/venus024/p/5699627.html
[Link 2]: http://www.cnblogs.com/venus024/p/5590044.html
[Link 3]: http://blog.csdn.net/thesby/article/details/52654519
[CVPR2016]: https://zhuanlan.zhihu.com/p/21533724
[Link 4]: http://blog.csdn.net/tiandijun/article/details/52251894
[Link 5]: http://www.thinkface.cn/thread-4434-1-1.html
[Deep Neural Networks for Object Detection]: http://blog.csdn.net/chenriwei2/article/details/38110541
[Link 6]: http://www.cnblogs.com/gujianhan/p/6025889.html
[DPMs are CNNs]: http://blog.csdn.net/cv_family_z/article/details/49449565
[- Object Detection from Video Tubelets with Convolutional Neural Networks]: http://blog.csdn.net/cv_family_z/article/details/52873045
[Exploit All the Layers_ Fast and Accurate CNN Object Detector with Scale Dependent Pooling and]: http://blog.csdn.net/cv_family_z/article/details/51273127
[Exploit All the Layers_ Fast and Accurate CNN Object Detector with Scale Dependent Pooling]: http://blog.csdn.net/cv_family_z/article/details/52022294
[Learning to Detect Vehicles by Clustering Appearance Patterns]: http://blog.csdn.net/cv_family_z/article/details/50524413
[Fast detection of multiple objects in traffic scenes with a common detection framework]: http://blog.csdn.net/cv_family_z/article/details/50174953
[3D Object Proposals for Accurate Object Class Detection]: http://blog.csdn.net/cv_family_z/article/details/49997563
[Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model]: http://blog.csdn.net/cv_family_z/article/details/49909291
[Filtered Channel Features for Pedestrian Detection]: http://blog.csdn.net/cv_family_z/article/details/48246491
[Taking a Deeper Look at Pedestrians]: http://blog.csdn.net/cv_family_z/article/details/48053535
[Pedestrian Detection aided by Deep Learning Semantic Tasks]: http://blog.csdn.net/cv_family_z/article/details/47259677
[Fast Feature Pyramids for Object Detection]: http://blog.csdn.net/cv_family_z/article/details/47810553
[Object Detection Using Generalization and Efficiency Balanced Co-occurrence Features]: http://blog.csdn.net/cv_family_z/article/details/50728989
[BING]: http://blog.csdn.net/cv_family_z/article/details/47130633
[BING_ A Fast High Quality Object Proposal Generator at 100fps]: http://blog.csdn.net/cv_family_z/article/details/50259773
[RNN]: http://blog.csdn.net/yaoxingfu72/article/details/51525878
[Beyond Skip Connections_ Top-Down Modulation for Object Detection]: http://blog.csdn.net/qq_29133371/article/details/54962575
[A-Fast-RCNN_ Hard Positive Generation via Adversary for Object Detection]: http://blog.csdn.net/cv_family_z/article/details/70156614
[A-Fast-RCNN_Caffe]: http://blog.csdn.net/u014380165/article/details/73069947
[A-Fast-RCNN]: http://blog.csdn.net/jesse_mx/article/details/72955981
[--Deep Self-Taught Learning for Weakly Supervised Object Localization]: http://blog.csdn.net/zhangjunhit/article/details/70674788
[Is object localization for free_ _ Weakly Supervised Object Recognition with Convolutional Neural Networks]: http://www.di.ens.fr/willow/research/weakcnn/
[Weakly Supervised Object Localization with Progressive Domain Adaptation]: https://sites.google.com/site/lidonggg930/wsl
[PASCAL VOC]: http://blog.csdn.net/zhangjunbob/article/details/52769381
[Pascal VOC]: http://blog.csdn.net/weixin_35653315/article/details/71028523
[VOC_mAP]: http://blog.csdn.net/lixiang_whu/article/details/64495093
[Faster-R-CNN_Python_.2_COCO_annotation]: http://blog.csdn.net/qq_30401249/article/details/72636414
[Bounding Box label code]: http://blog.csdn.net/qq_30401249/article/details/51504816
[Udacity Self-Driving]: http://blog.csdn.net/jesse_mx/article/details/72599220
[LabelImg]: http://blog.csdn.net/jesse_mx/article/details/53606897
[Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition 1]: http://blog.csdn.net/guojingjuan/article/details/50817829
[spp_net]: http://blog.csdn.net/guojingjuan/article/details/50948029
[spp_net _caffe]: http://blog.csdn.net/guojingjuan/article/details/51009315
[caffe_spp_net]: http://blog.csdn.net/guojingjuan/article/details/51014677
[spp_solver]: http://blog.csdn.net/guojingjuan/article/details/51024363
[spp_net 1]: http://blog.csdn.net/guojingjuan/article/details/51033907
[gpu_gtx1080_ cudnn 5.1_faster rcnn]: http://blog.csdn.net/qq_32270919/article/details/53026684
[FAST RCNN]: http://blog.csdn.net/dachao_xu/article/details/47321705
[fast-rcnn_demo.py_Ubuntu14.04]: http://blog.csdn.net/samylee/article/details/50965935
[faster-RCNN_buntu14.04]: http://blog.csdn.net/qq_26898461/article/details/50586242
[Faster RCNN 1]: http://blog.csdn.net/marshwb/article/details/50451548
[Py-faster-rcnn_train_demo]: http://blog.csdn.net/samylee/article/details/51201744
[Faster-RCNN_ZF_Python]: http://blog.csdn.net/sinat_30071459/article/details/51332084
[Faster-RCNN_VGG]: http://blog.csdn.net/sinat_30071459/article/details/50550607
[VOC2007_Faster-RCNN]: http://blog.csdn.net/sinat_30071459/article/details/50723212
[Faster R-CNN 3]: http://blog.csdn.net/WoPawn/article/details/52751614
[Faster-rcnn]: http://blog.csdn.net/kunhe0512/article/details/51396031
[Fast RCNN_ _2]: http://www.cnblogs.com/louyihang-loves-baiyan/p/4903231.html
[faster-rcnn]: http://blog.csdn.net/qq_26569761/article/details/51398656
[py-faster-rcnn_caffe_cudnn]: http://www.cnblogs.com/muchong/p/6101663.html
[RCNN_PASCAL VOC]: http://blog.csdn.net/liumaolincycle/article/details/50540487
[ImageNet_PASCAL VOC_xml]: http://blog.csdn.net/dyx810601/article/details/50587229
[python_VOC2007_xml]: http://blog.csdn.net/a130098300/article/details/53171484
[VOC_txt_lmdb]: http://blog.csdn.net/qq_29133371/article/details/54408165
[Faster rcnn 1]: http://blog.csdn.net/lilai619/article/details/53071155
[faster-rcnn 1]: http://blog.csdn.net/u011070171/article/details/52399317
[faster rcnn_assert _boxes_ 2_ _ boxes_ 0_.all_VOC2007 xml]: http://blog.csdn.net/10km/article/details/64641322
[faster-rcnn_assert_boxes_2_boxes_0_.all]: http://blog.csdn.net/xzzppp/article/details/52036794
[GTX1080_Cuda8.0_Cudnnv5_caffe_faster-rcnn]: http://blog.csdn.net/u010459819/article/details/53057171
[py-faster-rcnn_cuDNN V5]: http://blog.csdn.net/zhang_shuai12/article/details/62089246
[faster rcnn _cudnn V5]: http://blog.csdn.net/u010733679/article/details/52221404
[faster rcnn _cudnn V5 1]: http://blog.csdn.net/zouyu1746430162/article/details/54290327
[faster rcnn demo.py]: http://blog.csdn.net/10km/article/details/68926498
[TensorFlow _ Faster RCNN]: http://mp.weixin.qq.com/s/H1auL9Eawwev0v5j5QwGtg
[Faster-RCNN]: http://www.cnblogs.com/caffeaoto/p/6536482.html
[Faster RCNN 2]: http://blog.csdn.net/lixiang_whu/article/details/53785287
[Check rpn proposals in faster-rcnn]: http://blog.csdn.net/duinodu/article/details/53100919
[yolo-darknet]: http://blog.csdn.net/samylee/article/details/51684856
[yolo-darknet_train_test]: http://blog.csdn.net/samylee/article/details/51729729
[caffe _ yolo]: http://blog.csdn.net/u012235274/article/details/52120152
[YOLO 2]: http://blog.csdn.net/sinat_30071459/article/details/53100791
[YOLOv2_VOC]: http://blog.csdn.net/ch_liu23/article/details/53558549
[yolo]: http://blog.csdn.net/nnnnnnnnnnnny/article/details/53260355
[YOLO 3]: http://blog.csdn.net/nnnnnnnnnnnny/article/details/53017199
[yolo 1]: http://blog.csdn.net/nnnnnnnnnnnny/article/details/53924100
[YOLO_boundingbox]: http://blog.csdn.net/nnnnnnnnnnnny/article/details/54561928
[yolo 2]: http://blog.csdn.net/qq_30401249/article/details/51694298
[yolo 3]: http://blog.csdn.net/qq_30401249/article/details/51564871
[SSD 1]: http://blog.csdn.net/samylee/article/details/51822832
[SSD train your own data]: http://blog.csdn.net/samylee/article/details/51880039
[SSD_ Signle Shot Detector]: http://blog.csdn.net/u010167269/article/details/52851667
[SSD_ Single Shot MultiBox Detector_Linux]: http://blog.csdn.net/cosingne/article/details/53037889
[SSD_Single Shot MultiBox Detector_ubuntu16_VOC2007]: http://blog.csdn.net/10km/article/details/70168526
[SSD 2]: http://www.cnblogs.com/objectDetect/p/5780006.html
[resnet_ssd]: http://blog.csdn.net/zhangjunbob/article/details/53119959
[Single Shot Detection_SSD_bbox prediction]: http://blog.csdn.net/weixin_35653315/article/details/70940580
[Anchors in SSD]: http://blog.csdn.net/weixin_35653315/article/details/72288395
[SSD 3]: http://blog.csdn.net/weixin_35653315/article/details/72353346
[SSD_Matching Strategy]: http://blog.csdn.net/weixin_35653315/article/details/72357342
[ssd.pytorch]: https://github.com/amdegroot/ssd.pytorch
[caffe_pvanet_cuda7.5_VS2013]: http://blog.csdn.net/qq_29133371/article/details/53945143
[pva-faster-rcnn]: http://blog.csdn.net/qq_29133371/article/details/54582981
[pva faster rcnn]: http://blog.csdn.net/qq_29133371/article/details/55101907
[R-FCN_python]: http://blog.csdn.net/u010678153/article/details/52639267
[R-FCN_ResNet-50_python]: http://blog.csdn.net/sinat_30071459/article/details/53202977
[R-FCN_SSD_YOLO2_faster-rcnn_labelImg]: http://blog.csdn.net/mmmmmttttff/article/details/53243414