CASIA OpenIR
A Deep and Structured Metric Learning Method for Robust Person Re-Identification
Ren, Chuan-Xian1; Xu, Xiao-Lin2; Lei, Zhen3,4
Source PublicationPATTERN RECOGNITION
ISSN0031-3203
2019-12-01
Volume96Pages:12
Corresponding AuthorRen, Chuan-Xian()
AbstractPerson re-identification (re-ID) is to match different images of the same pedestrian. It has attracted increasing research interest in pattern recognition and machine learning. Traditionally, person re-ID is formulated as a metric learning problem with binary classification output. However, higher order relationship, such as triplet closeness among the instances, is ignored by such pair-wise based metric learning methods. Thus, the discriminative information hidden in these data is insufficiently explored. This paper proposes a new structured loss function to push the frontier of the person re-ID performance in realistic scenarios. The new loss function introduces two margin parameters. They operate as bounds to remove positive pairs of very small distances and negative pairs of large distances. A trade-off coefficient is assigned to the loss term of negative pairs to alleviate class-imbalance problem. By using a linear function with the margin-based objectives, the gradients w.r.t. weight matrices are no longer dependent on the iterative loss values in a multiplicative manner. This makes the weights update process robust to large iterative loss values. The new loss function is compatible with many deep learning architectures, thus, it induces new deep network with pair-pruning regularization for metric learning. To evaluate the performance of the proposed model, extensive experiments are conducted on benchmark datasets. The results indicate that the new loss together with the ResNet-50 backbone has excellent feature representation ability for person re-ID. (C) 2019 Elsevier Ltd. All rights reserved.
KeywordMetric learning Feature extraction Deep neural networks Imbalance regularization Person re-identification
DOI10.1016/j.patcog.2019.106995
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[61572536] ; National Natural Science Foundation of China[11631015] ; National Natural Science Foundation of China[U1611265] ; Science and Technology Program of GuangZhou[201804010248]
Funding OrganizationNational Natural Science Foundation of China ; Science and Technology Program of GuangZhou
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000487569700033
PublisherELSEVIER SCI LTD
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/26627
Collection中国科学院自动化研究所
Corresponding AuthorRen, Chuan-Xian
Affiliation1.Sun Yat Sen Univ, Sch Math, Intelligent Data Ctr, Guangzhou 510275, Guangdong, Peoples R China
2.Guangdong Univ Finance & Econ, Sch Math & Stat, Guangzhou 510320, Guangdong, Peoples R China
3.Chinese Acad Sci, Inst Automat, Ctr Biometr & Secur Res, Beijing 100190, Peoples R China
4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Ren, Chuan-Xian,Xu, Xiao-Lin,Lei, Zhen. A Deep and Structured Metric Learning Method for Robust Person Re-Identification[J]. PATTERN RECOGNITION,2019,96:12.
APA Ren, Chuan-Xian,Xu, Xiao-Lin,&Lei, Zhen.(2019).A Deep and Structured Metric Learning Method for Robust Person Re-Identification.PATTERN RECOGNITION,96,12.
MLA Ren, Chuan-Xian,et al."A Deep and Structured Metric Learning Method for Robust Person Re-Identification".PATTERN RECOGNITION 96(2019):12.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Ren, Chuan-Xian]'s Articles
[Xu, Xiao-Lin]'s Articles
[Lei, Zhen]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ren, Chuan-Xian]'s Articles
[Xu, Xiao-Lin]'s Articles
[Lei, Zhen]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ren, Chuan-Xian]'s Articles
[Xu, Xiao-Lin]'s Articles
[Lei, Zhen]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.