Unsupervised Person Re-identification via Cross-camera Similarity Exploration.

Lin, Y; Wu, Y; Yan, C; Xu, M; Yang, Y

Unsupervised Person Re-identification via Cross-camera Similarity Exploration.

Lin, Y Wu, Y

Yan, C Xu, M Yang, Y

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Journal Article
Citation:: IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 2020, 29, pp. 5481-5490
Issue Date:: 2020-04

Closed Access

	Filename	Description	Size
	09052758.pdf	Published version	2.23 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Lin, Y
dc.contributor.author	Wu, Y https://orcid.org/0000-0002-1680-8253
dc.contributor.author	Yan, C
dc.contributor.author	Xu, M
dc.contributor.author	Yang, Y https://orcid.org/0000-0001-5528-0546
dc.date.accessioned	2021-02-09T03:16:11Z
dc.date.available	2021-02-09T03:16:11Z
dc.date.issued	2020-04
dc.identifier.citation	IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 2020, 29, pp. 5481-5490
dc.identifier.issn	1057-7149
dc.identifier.issn	1941-0042
dc.identifier.uri	http://hdl.handle.net/10453/145975
dc.description.abstract	Most person re-identification (re-ID) approaches are based on supervised learning, which requires manually annotated data. However, it is not only resource-intensive to acquire identity annotation but also impractical for large-scale data. To relieve this problem, we propose a cross-camera unsupervised approach that makes use of unsupervised style-transferred images to jointly optimize a convolutional neural network (CNN) and the relationship among the individual samples for person re-ID. Our algorithm considers two fundamental facts in the re- ID task, i.e., variance across diverse cameras and similarity within the same identity. In this paper, we propose an iterative framework which overcomes the camera variance and achieves across-camera similarity exploration. Specifically, we apply an unsupervised style transfer model to generate style-transferred training images with different camera styles. Then we iteratively exploit the similarity within the same identity from both the original and the style-transferred data. We start with considering each training image as a different class to initialize the Convolutional Neural Network (CNN) model. Then we measure the similarity and gradually group similar samples into one class, which increases similarity within each identity. We also introduce a diversity regularization term in the clustering to balance the cluster distribution. The experimental results demonstrate that our algorithm is not only superior to state-of-the-art unsupervised re-ID approaches, but also performs favorably compared with other competing unsupervised domain adaptation methods (UDA) and semi-supervised learning methods.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
dc.relation.isbasedon	10.1109/tip.2020.2982826
dc.rights	© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.	en_US
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0906 Electrical and Electronic Engineering, 1702 Cognitive Sciences
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Unsupervised Person Re-identification via Cross-camera Similarity Exploration.
dc.type	Journal Article
utslib.citation.volume	29
utslib.location.activity	United States
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	1702 Cognitive Sciences
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2021-02-09T03:16:02Z
pubs.publication-status	Published
pubs.volume	29

Abstract:

Most person re-identification (re-ID) approaches are based on supervised learning, which requires manually annotated data. However, it is not only resource-intensive to acquire identity annotation but also impractical for large-scale data. To relieve this problem, we propose a cross-camera unsupervised approach that makes use of unsupervised style-transferred images to jointly optimize a convolutional neural network (CNN) and the relationship among the individual samples for person re-ID. Our algorithm considers two fundamental facts in the re- ID task, i.e., variance across diverse cameras and similarity within the same identity. In this paper, we propose an iterative framework which overcomes the camera variance and achieves across-camera similarity exploration. Specifically, we apply an unsupervised style transfer model to generate style-transferred training images with different camera styles. Then we iteratively exploit the similarity within the same identity from both the original and the style-transferred data. We start with considering each training image as a different class to initialize the Convolutional Neural Network (CNN) model. Then we measure the similarity and gradually group similar samples into one class, which increases similarity within each identity. We also introduce a diversity regularization term in the clustering to balance the cluster distribution. The experimental results demonstrate that our algorithm is not only superior to state-of-the-art unsupervised re-ID approaches, but also performs favorably compared with other competing unsupervised domain adaptation methods (UDA) and semi-supervised learning methods.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/145975