Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification

doi:10.1109/TITS.2022.3224233

	Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification
	Xu, Mingyuan 1; Guo, Haiyun2,3 ; Jia, Yuheng 4,5; Dai, Zhitao 1; Wang, Jinqiao3,6
发表期刊	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
ISSN	1524-9050
	2022-11-30
页码	12
通讯作者	Guo, Haiyun(haiyun.guo@nlpr.ia.ac.cn) ; Jia, Yuheng(yhjia@seu.edu.cn)
摘要	Person re-identification (re-ID) has many applications in intelligent transportation systems. Clustering-based methods, which alternate between the generation of pseudo labels via clustering and the optimization of the feature extractor, have obtained leading performance in unsupervised person re-ID. But there are still two issues not well addressed: 1) Most methods measure the feature similarity without considering the domain shift between cameras, degrading the clustering performance. 2) Outliers, which usually correspond to hard samples with large discrepancy from other images of the identical person, are in most cases directly excluded from the network training. To tackle the above issues, this paper proposes a plug-and-play pseudo label rectification framework, which jointly utilizes CAmera Shift adapTation module and Outlier progressive Recycling strategy ( $CASTOR$ ) to improve the quality of pseudo labels from both pre-clustering and post-clustering. Specifically, we first compute the camera similarity of two samples by utilizing a pretrained camera classification network and subtract the feature similarity by the camera similarity, the value of which is weighted in an exponential decay manner throughout the network training, in order to adaptively remedy the adverse impact of inter-camera distribution shift upon clustering. Besides, we carefully design an outlier progressive recycling strategy to reassign part of the outliers into the clustered groups to make full use of the useful information of outliers. Extensive experiments on three large scale unsupervised and unsupervised domain adaptive (UDA) person re-ID benchmarks validate the effectiveness of CASTOR and its wide compatibility with the state-of-the-art clustering-based methods.
关键词	Person re-identification unsupervised learning domain adaptation pseudo label rectification
DOI	10.1109/TITS.2022.3224233
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2021ZD0110403] ; National Natural Science Foundation of China[62002356] ; National Natural Science Foundation of China[62106044] ; National Natural Science Foundation of China[62002357] ; National Natural Science Foundation of China[62076235] ; Natural Science Foundation of Jiangsu Province[BK20210221] ; Zhejiang Laboratory[2021KH0AB07]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Natural Science Foundation of Jiangsu Province ; Zhejiang Laboratory
WOS研究方向	Engineering ; Transportation
WOS类目	Engineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS记录号	WOS:000912859500001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：3[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/173211/51067
专题	紫东太初大模型研究中心_图像与视频分析
通讯作者	Guo, Haiyun; Jia, Yuheng
作者单位	1.Beijing Univ Posts & Telecommun, Sch Comp Sci, Beijing 100864, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China 4.Southeast Univ, Key Lab Comp Network & Informat Integrat, Minist Educ, Nanjing 210096, Peoples R China 5.Southeast Univ, Sch Comp Sci & Engn, Nanjing 210096, Peoples R China 6.Peng Cheng Lab, Shenzhen 518066, Peoples R China
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	Xu, Mingyuan,Guo, Haiyun,Jia, Yuheng,et al. Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2022:12.
APA	Xu, Mingyuan,Guo, Haiyun,Jia, Yuheng,Dai, Zhitao,&Wang, Jinqiao.(2022).Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,12.
MLA	Xu, Mingyuan,et al."Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022):12.