中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能感知与计算研究中心
Feedback Convolutional Neural Network for Visual Localization and Segmentation

文献类型：期刊论文

作者Cao, Chunshui1,2; Huang, Yongzhen3,4; Yang, Yi5; Wang, Liang3,4; Wang, Zilei1; Tan, Tieniu3,4
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2019-07-01
卷号41期号:7页码:1627-1640
ISSN号0162-8828
关键词feedback convolutional neural networks (CNNs) weakly supervised object localization object segmentation
DOI10.1109/TPAMI.2018.2843329
通讯作者Cao, Chunshui(ccs@mail.ustc.edu.cn)
英文摘要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.
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]
WOS研究方向Computer Science ; Engineering
语种英语
出版者IEEE COMPUTER SOC
WOS记录号WOS:000470972300008
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/26027]  
专题自动化研究所_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
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.

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

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。