中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Feedback Convolutional Neural Network for Visual Localization and Segmentation

文献类型:期刊论文

AuthorCao, Chunshui1,2; Huang, Yongzhen3,4; Yang, Yi5; Wang, Liang3,4; Wang, Zilei1; Tan, Tieniu3,4
SourceIEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Issued Date2019-07-01
Volume41Issue:7Pages:1627-1640
Keywordfeedback convolutional neural networks (CNNs) weakly supervised object localization object segmentation
ISSN0162-8828
DOI10.1109/TPAMI.2018.2843329
Corresponding AuthorCao, Chunshui(ccs@mail.ustc.edu.cn)
English AbstractFeedback 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.
Funding ProjectNational Key Research and Development Program of China[2016YFB1001000] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61420106015]
WOS Research AreaComputer Science ; Engineering
Language英语
PublisherIEEE COMPUTER SOC
WOS IDWOS:000470972300008
Funding OrganizationNational Key Research and Development Program of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/26027]  
Collection自动化研究所_智能感知与计算研究中心
Corresponding AuthorCao, Chunshui
Affiliation1.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
Recommended Citation
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.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.