[原创]Faster R-CNN论文翻译
Faster R-CNN论文翻译
Faster R-CNN是互怼完了的好基友一起合作出来的巅峰之作,本文翻译的比例比较小,主要因为本paper是前述paper的一个简单改进,方法清晰,想法自然。什么想法?就是把那个一直明明应该换掉却一直被几位大神挤牙膏般地拖着不换的选择性搜索算法,即区域推荐算法。在Fast R-CNN的基础上将区域推荐换成了神经网络,而且这个神经网络和Fast R-CNN的卷积网络一起复用,大大缩短了计算时间。同时mAP又上了一个台阶,我早就说过了,他们一定是在挤牙膏。
Faster R-CNN: Towards Real-Time Object
Detection with Region Proposal Networks
摘要
1. 介绍

2 相关工作
3 FASTER R-CNN

3.1 区域推荐网络

3.1.1 锚点
平移不变性锚点
多尺度锚点作为回归参照物
3.1.2 损失函数




3.1.3 训练RPNs
3.2 RPN and Fast R-CNN之间共享特征
3.3 实现细节
4 EXPERIMENTS
5 CONCLUSION
参考文献
[2] R. Girshick, “Fast R-CNN,” in IEEE International Conference onComputer Vision (ICCV), 2015.
[3] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in InternationalConference on Learning Representations (ICLR), 2015.
[4] J. R. Uijlings, K. E. van de Sande, T. Gevers, and A. W. Smeulders, “Selective search for object recognition,” InternationalJournal of Computer Vision (IJCV), 2013.
[5] R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich featurehierarchies for accurate object detection and semantic segmentation,” in IEEE Conference on Computer Vision and PatternRecognition (CVPR), 2014.
[6] C. L. Zitnick and P. Dollar, “Edge boxes: Locating object ´proposals from edges,” in European Conference on ComputerVision (ECCV), 2014.
[7] J. Long, E. Shelhamer, and T. Darrell, “Fully convolutionalnetworks for semantic segmentation,” in IEEE Conference onComputer Vision and Pattern Recognition (CVPR), 2015.
[8] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, “Object detection with discriminatively trained partbased models,” IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2010.
[9] P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus,and Y. LeCun, “Overfeat: Integrated recognition, localizationand detection using convolutional networks,” in InternationalConference on Learning Representations (ICLR), 2014.
[10] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,” inNeural Information Processing Systems (NIPS), 2015.
[11] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, andA. Zisserman, “The PASCAL Visual Object Classes Challenge2007 (VOC2007) Results,” 2007.
[12] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollar, and C. L. Zitnick, “Microsoft COCO: Com- ´mon Objects in Context,” in European Conference on ComputerVision (ECCV), 2014.
[13] S. Song and J. Xiao, “Deep sliding shapes for amodal 3d objectdetection in rgb-d images,” arXiv:1511.02300, 2015.
[14] J. Zhu, X. Chen, and A. L. Yuille, “DeePM: A deep part-basedmodel for object detection and semantic part localization,”arXiv:1511.07131, 2015.
[15] J. Dai, K. He, and J. Sun, “Instance-aware semantic segmentation via multi-task network cascades,” arXiv:1512.04412, 2015.
[16] J. Johnson, A. Karpathy, and L. Fei-Fei, “Densecap: Fullyconvolutional localization networks for dense captioning,”arXiv:1511.07571, 2015.
[17] D. Kislyuk, Y. Liu, D. Liu, E. Tzeng, and Y. Jing, “Human curation and convnets: Powering item-to-item recommendationson pinterest,” arXiv:1511.04003, 2015.
[18] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learningfor image recognition,” arXiv:1512.03385, 2015.
[19] J. Hosang, R. Benenson, and B. Schiele, “How good are detection proposals, really?” in British Machine Vision Conference(BMVC), 2014.
[20] J. Hosang, R. Benenson, P. Dollar, and B. Schiele, “What makes ´for effective detection proposals?” IEEE Transactions on PatternAnalysis and Machine Intelligence (TPAMI), 2015.
[21] N. Chavali, H. Agrawal, A. Mahendru, and D. Batra,“Object-Proposal Evaluation Protocol is ’Gameable’,” arXiv:1505.05836, 2015.
[22] J. Carreira and C. Sminchisescu, “CPMC: Automatic object segmentation using constrained parametric min-cuts,”IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2012.
[23] P. Arbelaez, J. Pont-Tuset, J. T. Barron, F. Marques, and J. Malik, ´“Multiscale combinatorial grouping,” in IEEE Conference onComputer Vision and Pattern Recognition (CVPR), 2014.
[24] B. Alexe, T. Deselaers, and V. Ferrari, “Measuring the objectness of image windows,” IEEE Transactions on Pattern Analysisand Machine Intelligence (TPAMI), 2012.
[25] C. Szegedy, A. Toshev, and D. Erhan, “Deep neural networksfor object detection,” in Neural Information Processing Systems(NIPS), 2013.
[26] D. Erhan, C. Szegedy, A. Toshev, and D. Anguelov, “Scalableobject detection using deep neural networks,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
[27] C. Szegedy, S. Reed, D. Erhan, and D. Anguelov, “Scalable,high-quality object detection,” arXiv:1412.1441 (v1), 2015.
[28] P. O. Pinheiro, R. Collobert, and P. Dollar, “Learning tosegment object candidates,” in Neural Information ProcessingSystems (NIPS), 2015.
[29] J. Dai, K. He, and J. Sun, “Convolutional feature maskingfor joint object and stuff segmentation,” in IEEE Conference onComputer Vision and Pattern Recognition (CVPR), 2015.
[30] S. Ren, K. He, R. Girshick, X. Zhang, and J. Sun, “Object detection networks on convolutional feature maps,”arXiv:1504.06066, 2015.
[31] J. K. Chorowski, D. Bahdanau, D. Serdyuk, K. Cho, andY. Bengio, “Attention-based models for speech recognition,”in Neural Information Processing Systems (NIPS), 2015.
[32] M. D. Zeiler and R. Fergus, “Visualizing and understandingconvolutional neural networks,” in European Conference onComputer Vision (ECCV), 2014.
[33] V. Nair and G. E. Hinton, “Rectified linear units improverestricted boltzmann machines,” in International Conference onMachine Learning (ICML), 2010.
[34] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov,D. Erhan, and A. Rabinovich, “Going deeper with convolutions,” in IEEE Conference on Computer Vision and PatternRecognition (CVPR), 2015.
[35] Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard,W. Hubbard, and L. D. Jackel, “Backpropagation applied tohandwritten zip code recognition,” Neural computation, 1989.
[36] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma,Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg,and L. Fei-Fei, “ImageNet Large Scale Visual RecognitionChallenge,” in International Journal of Computer Vision (IJCV),2015.
[37] A. Krizhevsky, I. Sutskever, and G. Hinton, “Imagenet classification with deep convolutional neural networks,” in NeuralInformation Processing Systems (NIPS), 2012.
[38] Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell, “Caffe: Convolutionalarchitecture for fast feature embedding,” arXiv:1408.5093, 2014.
[39] K. Lenc and A. Vedaldi, “R-CNN minus R,” in British MachineVision Conference (BMVC), 2015.
[原创]Faster R-CNN论文翻译的更多相关文章
- k[原创]Faster R-CNN论文翻译
物体检测论文翻译系列: 建议从前往后看,这些论文之间具有明显的延续性和递进性. R-CNN SPP-net Fast R-CNN Faster R-CNN Faster R-CNN论文翻译 原文地 ...
- 深度学习论文翻译解析(四):Faster R-CNN: Down the rabbit hole of modern object detection
论文标题:Faster R-CNN: Down the rabbit hole of modern object detection 论文作者:Zhi Tian , Weilin Huang, Ton ...
- 深度学习论文翻译解析(十三):Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
论文标题:Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks 标题翻译:基于区域提议(Regi ...
- 深度学习论文翻译解析(三):Detecting Text in Natural Image with Connectionist Text Proposal Network
论文标题:Detecting Text in Natural Image with Connectionist Text Proposal Network 论文作者:Zhi Tian , Weilin ...
- 深度学习论文翻译解析(十六):Squeeze-and-Excitation Networks
论文标题:Squeeze-and-Excitation Networks 论文作者:Jie Hu Li Shen Gang Sun 论文地址:https://openaccess.thecvf.co ...
- R-CNN论文翻译
R-CNN论文翻译 Rich feature hierarchies for accurate object detection and semantic segmentation 用于精确物体定位和 ...
- SSD: Single Shot MultiBoxDetector英文论文翻译
SSD英文论文翻译 SSD: Single Shot MultiBoxDetector 2017.12.08 摘要:我们提出了一种使用单个深层神经网络检测图像中对象的方法.我们的方法,名为SSD ...
- 深度学习论文翻译解析(二):An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
论文标题:An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application ...
- 论文翻译——R-CNN(目标检测开山之作)
R-CNN论文翻译 <Rich feature hierarchies for accurate object detection and semantic segmentation> 用 ...
随机推荐
- #define WIN32_LEAN_AND_MEAN
不加载MFC所需的模块.用英语解释:Say no to MFC如果你的工程不使用MFC,就加上这句,这样一来在编译链接时,包括最后生成的一些供调试用的模块时,速度更快,容量更小.不过对于较大工程,MF ...
- 使用Xshell+Xmanager远程监控jvisualvm
使用jvisualvm的remote方式监控服务器端jvisualvm时,不是很方便,因此通过local方式,应该是正路. 一.服务器端(Linux,最小安装模式,没有图形界面) 1.安装xauth ...
- SpringBoot初体验
1.elipse中创建Springboot项目并启动 具体创建步骤请参考:Eclipse中创建新的Spring Boot项目 2.项目的属性配置 a.首先我们在项目的resources目录下appli ...
- zoj 1889 ones 数学
Ones Time Limit: 2 Seconds Memory Limit: 65536 KB Given any integer 0 <= n <= 10000 not d ...
- IDL 数组运算
1.求大.求小和求余 IDL> arr=indgen(4) IDL> print,arr 0 1 2 3 IDL> print,arr>3 3 3 3 3 IDL> pr ...
- 用SqlCommandBuilder 实现批量更新
一般是这样的,如果用设计器将SqlDataAdapter拖到页面中使用时,不会出现SqlDataAdapter.Update(ds)更新时出错情况,因为系统会自动生成SqlDataAdapter的属性 ...
- cocos2dx - 创建地图及玩家(伪)
接上一节内容:cocos2dx - 环境配置,项目创建 本节主要描述cocos中精灵的创建及点击事件的使用 打开创建好的test项目,看到下图的目录结构,真正的游戏逻辑路径在src下. AppDele ...
- CoreData归纳使用
1.CoreData简介 2.CoreData数据模型 3.CoreData的主要对象 4.使用CoreData实现数据存储 一.CoreData简介 CoreData用做数据持久化,是数据持久化的最 ...
- Java简单知识梳理
1. Java是单根继承结构:每个类都继承于Object类 ,这也就保证了每个对象都具备某些功能 2. Java类权限关键字: public -> protected -> default ...
- 我的three.js学习记录(三)
此次的亮点不是three.js的3d部分,而是通过调用摄像头然后通过摄像头的图像变化进行简单的判断后进行一些操作.上篇中我通过简单的示例分析来学习three.js,这次是通过上一篇的一些代码来与摄像头 ...