Feedback Convolutional Neural Network for Visual Localization and Segmentation

doi:10.1109/TPAMI.2018.2843329

CASIA OpenIR > 智能感知与计算研究中心

	Feedback Convolutional Neural Network for Visual Localization and Segmentation
	Cao, Chunshui1,2 ; Huang, Yongzhen3,4 ; Yang, Yi 5; Wang, Liang3,4 ; Wang, Zilei 1; Tan, Tieniu3,4
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
	2019-07-01
卷号	41 期号:7 页码:1627-1640
通讯作者	Cao, Chunshui(ccs@mail.ustc.edu.cn)
摘要	Feedback is a fundamental mechanism existing in the human visual system, but has not been explored deeply in designing computer vision algorithms. In this paper, we claim that feedback plays a critical role in understanding convolutional neural networks (CNNs), e.g., how a neuron in CNNs describes an object's pattern, and how a collection of neurons form comprehensive perception to an object. To model the feedback in CNNs, we propose a novel model named Feedback CNN and develop two new processing algorithms, i.e., neural pathway pruning and pattern recovering. We mathematically prove that the proposed method can reach local optimum. Note that Feedback CNN belongs to weakly supervised methods and can be trained only using category-level labels. But it possesses a powerful capability to accurately localize and segment category-specific objects. We conduct extensive visualization analysis, and the results reveal the close relationship between neurons and object parts in Feedback CNN. Finally, we evaluate the proposed Feedback CNN over the tasks of weakly supervised object localization and segmentation, and the experimental results on ImageNet and Pascal VOC show that our method remarkably outperforms the state-of-the-art ones.
关键词	feedback convolutional neural networks (CNNs) weakly supervised object localization object segmentation
DOI	10.1109/TPAMI.2018.2843329
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2016YFB1001000] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61420106015] ; National Key Research and Development Program of China[2016YFB1001000] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61420106015]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000470972300008
出版者	IEEE COMPUTER SOC
七大方向——子方向分类	计算机图形学与虚拟现实
引用统计	被引频次：21[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/26028
专题	智能感知与计算研究中心
通讯作者	Cao, Chunshui
作者单位	1.Univ Sci & Technol China, Hefei 230000, Anhui, Peoples R China 2.Chinese Acad Sci CASIA, Ctr Res Intelligent Percept & Comp CRIPAC, NLPR, Inst Automat, Beijing 100864, Peoples R China 3.Univ Chinese Acad Sci, Huairou 101408, Peoples R China 4.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China 5.Baidu Res, Sunnyvale, CA 94089 USA
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Cao, Chunshui,Huang, Yongzhen,Yang, Yi,et al. Feedback Convolutional Neural Network for Visual Localization and Segmentation[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2019,41(7):1627-1640.
APA	Cao, Chunshui,Huang, Yongzhen,Yang, Yi,Wang, Liang,Wang, Zilei,&Tan, Tieniu.(2019).Feedback Convolutional Neural Network for Visual Localization and Segmentation.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,41(7),1627-1640.
MLA	Cao, Chunshui,et al."Feedback Convolutional Neural Network for Visual Localization and Segmentation".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 41.7(2019):1627-1640.