Feedback mechanism based iterative metric learning for person re-identification

doi:10.1016/j.patcog.2017.04.012

CORC > 西安光学精密机械研究所 > 中国科学院西安光学精密机械研究所 > 光学影像学习与分析中心

	Feedback mechanism based iterative metric learning for person re-identification
	Ren, Yutao 1,2; Li, Xuelong2 ; Lu, Xiaoqiang2
刊名	PATTERN RECOGNITION
	2018-03-01
卷号	75 页码:99-111
关键词	Person Re-identification Metric Learning Feedback Iteration
ISSN号	0031-3203
DOI	10.1016/j.patcog.2017.04.012
产权排序	1
英文摘要	Person re-identification problem is targeting to match people in the views of non-overlapped camera networks. It is an important task in the fields of computer vision and video surveillance. It shows great value in applications like surveillance and action recognition. Existing metric learning based methods measure the similarity of sample pairs by learning a metric space in which the positive pairs are closer than negative pairs. However, the appearance features undergo with drastic variation. Person re-identification is a typical small sample problem. It is hard to learn a robust projection of metric subspace that takes all the situations into consideration. The learned metric subspace is usually over-fitting to training dataset due to the strict metric learning constraint. And the hard pairs in training dataset will weaken the discrimination of matching pairs' similarity. To address these problems, a feedback mechanism based iterative metric learning method is proposed. The proposed method introduces a mean distance of multi-metric subspace to deal with the over-fitting problem. The joint discriminant optimal model on feedback top ranks matching pairs will enhance the discrimination of matching pairs' similarity. It is a robust and discriminative distance metric which measures the matching pairs similarity with distances of multiple metric projections learned by a set of training datasets. Aiming to learn the multi-metric subspace, the proposed method gives a feedback mechanism based approach which back propagates the top ranks identification results as pseudo training datasets. The effectiveness of proposed mean distance of multi-metric projection is analyzed and proved theoretically. And extensive experiments on three challenging datasets, VIPeR, GRID and CUHK01 are conducted. The results show that the proposed method achieves the best performance and improves the state-of-the-art rank-1 identification rates by 18.48%, 2.00% and 5.41% on three datasets respectively. (C) 2017 Elsevier Ltd. All rights reserved.
语种	英语
WOS记录号	WOS:000418971900011
内容类型	期刊论文
源URL	[http://ir.opt.ac.cn/handle/181661/30815]
专题	西安光学精密机械研究所_光学影像学习与分析中心
作者单位	1.Wuhan Univ Technol, Wuhan 430070, Hubei, Peoples R China; 2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr OPT IMagery Anal & Learning OPTIMAL, State Key Lab Transient Opt & Photon, Xian 710119, Shaanxi, Peoples R China
推荐引用方式 GB/T 7714	Ren, Yutao,Li, Xuelong,Lu, Xiaoqiang. Feedback mechanism based iterative metric learning for person re-identification[J]. PATTERN RECOGNITION,2018,75:99-111.
APA	Ren, Yutao,Li, Xuelong,&Lu, Xiaoqiang.(2018).Feedback mechanism based iterative metric learning for person re-identification.PATTERN RECOGNITION,75,99-111.
MLA	Ren, Yutao,et al."Feedback mechanism based iterative metric learning for person re-identification".PATTERN RECOGNITION 75(2018):99-111.