Improve Person Re-Identification With Part Awareness Learning

doi:10.1109/TIP.2020.3003442

	Improve Person Re-Identification With Part Awareness Learning
	Huang, Houjing 6,7; Yang, Wenjie 6,7; Lin, Jinbin 5; Huang, Guan 4,5; Xu, Jiamiao 2,3,5; Wang, Guoli 5; Chen, Xiaotang 6,7; Huang, Kaiqi 1,6,7
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2020
卷号	29 页码:7468-7481
关键词	Person re-identification part awareness part segmentation multi-task learning
ISSN号	1057-7149
DOI	10.1109/TIP.2020.3003442
通讯作者	Huang, Houjing(houjing.huang@nlpr.ia.ac.cn)
英文摘要	Person re-identification (ReID) aims to predict whether two images from different cameras belong to the same person. Due to low image quality and variance in view point and body pose, it remains a difficult task. To solve the task, a model is supposed to appropriately capture features that describe body regions for identification. With the simple intuition that explicitly incorporating ReID model with part awareness could be beneficial for learning a more discriminative feature space, we propose part segmentation as an assistant body perception task during the training of a ReID model. Specifically, we add a lightweight segmentation head to the backbone of ReID model during training, which is supervised with part labels. Note that our segmentation head is only introduced during training and that it does not change network input or the way of extracting ReID feature. Experiments show that part segmentation considerably improves the performance of ReID. Through quantitative and qualitative analyses, we further reveal that body part perception helps ReID model to capture a set of more diverse features from the body, with decreased similarity between part features and increased focus on different body regions. We experiment with various representative ReID models and achieve consistent improvement on several large-scale datasets including Market1501, CUHK03, DukeMTMC-reID and MSMT17. E.g. on MSMT17, our method increases Rank-1 Accuracy of GlobalPool-ResNet-50, PCB and MGN by 2.3%, 2.9% and 3.9%, respectively. Incorporated with MGN, our model achieves state-of-the-art performance, with Rank-1 Accuracy 95.8%, 78.8%, 90.0% and 84.0% on four datasets, respectively.
资助项目	National Key Research and Development Program of China[2016YFB1001005] ; National Natural Science Foundation of China[61673375] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61876181] ; Projects of Chinese Academy of Science[QYZDB-SSW-JSC006] ; Youth Innovation Promotion Association CAS
WOS关键词	NETWORK
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000553851400017
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Projects of Chinese Academy of Science ; Youth Innovation Promotion Association CAS
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/40262]
专题	智能系统与工程
通讯作者	Huang, Houjing
作者单位	1.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China 2.DeepRouteai, Deep Learning Dept, Shenzhen 518000, Peoples R China 3.Huazhong Univ Sci & Technol, Sch Elect Informat & Commun, Wuhan 430074, Peoples R China 4.Xforward AI Technol Co Ltd, Algorithm Dept, Beijing 100081, Peoples R China 5.Horizon Robot Inc, Beijing 100036, Peoples R China 6.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 7.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Syst & Engn, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Huang, Houjing,Yang, Wenjie,Lin, Jinbin,et al. Improve Person Re-Identification With Part Awareness Learning[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:7468-7481.
APA	Huang, Houjing.,Yang, Wenjie.,Lin, Jinbin.,Huang, Guan.,Xu, Jiamiao.,...&Huang, Kaiqi.(2020).Improve Person Re-Identification With Part Awareness Learning.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,7468-7481.
MLA	Huang, Houjing,et al."Improve Person Re-Identification With Part Awareness Learning".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):7468-7481.