Deep Representation Learning With Part Loss for Person Re-Identification

doi:10.1109/TIP.2019.2891888

	Deep Representation Learning With Part Loss for Person Re-Identification
	Yao, Hantao 1; Zhang, Shiliang 2; Hong, Richang 3; Zhang, Yongdong 4; Xu, Changsheng 1,5; Tian, Qi 6
	2019-06-01
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	28 期号:6 页码:2860-2871
摘要	Learning discriminative representations for unseen person images is critical for person re-identification (ReID). Most of the current approaches learn deep representations in classification tasks, which essentially minimize the empirical classification risk on the training set. As shown in our experiments, such representations easily get over-fitted on a discriminative human body part on the training set. To gain the discriminative power on unseen person images, we propose a deep representation learning procedure named part loss network, to minimize both the empirical classification risk on training person images and the representation learning risk on unseen person images. The representation learning risk is evaluated by the proposed part loss, which automatically detects human body parts and computes the person classification loss on each part separately. Compared with traditional global classification loss, simultaneously considering part loss enforces the deep network to learn representations for different body parts and gain the discriminative power on unseen persons. Experimental results on three person ReID datasets, i.e., Market1501, CUHK03, and VIPeR, show that our representation outperforms existing deep representations.
关键词	Person re-identification representation learning part lass networks convolutional neural networks
DOI	10.1109/TIP.2019.2891888
收录类别	SCI
语种	英语
资助项目	National Postdoctoral Programme for Innovative Talents ; National Nature Science Foundation of China[61525206] ; National Nature Science Foundation of China[61532009] ; National Nature Science Foundation of China[61721004] ; National Nature Science Foundation of China[U1705262] ; National Nature Science Foundation of China[61572050] ; National Nature Science Foundation of China[91538111] ; National Nature Science Foundation of China[61620106009] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000462386000018
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：296[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/4140
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Yao, Hantao
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Peking Univ, Sch Elect Engn & Comp Sci, Beijing 100871, Peoples R China 3.Univ Technol, Dept Comp Sci & Technol, Hefei 230009, Anhui, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 5.Univ Chinese Acad Sci, Dept Artificial Intelligence, Beijing 100049, Peoples R China 6.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA
推荐引用方式 GB/T 7714	Yao, Hantao,Zhang, Shiliang,Hong, Richang,et al. Deep Representation Learning With Part Loss for Person Re-Identification[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2019,28(6):2860-2871.
APA	Yao, Hantao,Zhang, Shiliang,Hong, Richang,Zhang, Yongdong,Xu, Changsheng,&Tian, Qi.(2019).Deep Representation Learning With Part Loss for Person Re-Identification.IEEE TRANSACTIONS ON IMAGE PROCESSING,28(6),2860-2871.
MLA	Yao, Hantao,et al."Deep Representation Learning With Part Loss for Person Re-Identification".IEEE TRANSACTIONS ON IMAGE PROCESSING 28.6(2019):2860-2871.