Learning to Adapt Invariance in Memory for Person Re-identification.

Zhong, Z; Zheng, L; Luo, Z; Li, S; Yang, Y

Learning to Adapt Invariance in Memory for Person Re-identification.

Zhong, Z Zheng, L Luo, Z Li, S Yang, Y

Permalink

Publisher:: Institute of Electrical and Electronics Engineers
Publication Type:: Journal Article
Citation:: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43, (8), pp. 2723-2738
Issue Date:: 2021

Closed Access

	Filename	Description	Size
	Learning_to_Adapt_Invariance_in_Memory_for_Person_Re-Identification.pdf	Published version	1.71 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	Zhong, Z
dc.contributor.author	Zheng, L
dc.contributor.author	Luo, Z
dc.contributor.author	Li, S
dc.contributor.author	Yang, Y https://orcid.org/0000-0002-0512-880X
dc.date.accessioned	2022-05-07T23:58:39Z
dc.date.available	2022-05-07T23:58:39Z
dc.date.issued	2021
dc.identifier.citation	IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43, (8), pp. 2723-2738
dc.identifier.issn	0162-8828
dc.identifier.issn	1939-3539
dc.identifier.uri	http://hdl.handle.net/10453/157124
dc.description.abstract	This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain. Existing methods are primary to reduce the inter-domain shift between the domains, which however usually overlook the relations among target samples. This paper investigates into the intra-domain variations of the target domain and proposes a novel adaptation framework w.r.t three types of underlying invariance, i.e., Exemplar-Invariance, Camera-Invariance, and Neighborhood-Invariance. Specifically, an exemplar memory is introduced to store features of samples, which can effectively and efficiently enforce the invariance constraints over the global dataset. We further present the Graph-based Positive Prediction (GPP) method to explore reliable neighbors for the target domain, which is built upon the memory and is trained on the source samples. Experiments demonstrate that 1) the three invariance properties are complementary and indispensable for effective domain adaptation, 2) the memory plays a key role in implementing invariance learning and improves the performance with limited extra computation cost, 3) GPP can facilitate the invariance learning and thus significantly improves the results, and 4) our approach produces new state-of-the-art adaptation accuracy on three re-ID large-scale benchmarks.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	Institute of Electrical and Electronics Engineers
dc.relation.ispartof	IEEE Transactions on Pattern Analysis and Machine Intelligence
dc.relation.isbasedon	10.1109/tpami.2020.2976933
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0806 Information Systems, 0906 Electrical and Electronic Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Learning to Adapt Invariance in Memory for Person Re-identification.
dc.type	Journal Article
utslib.citation.volume	43
utslib.location.activity	United States
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0806 Information Systems
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	/University of Technology Sydney
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
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2022-05-07T23:58:36Z
pubs.issue	8
pubs.publication-status	Published
pubs.volume	43
utslib.citation.issue	8

Abstract:

This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain. Existing methods are primary to reduce the inter-domain shift between the domains, which however usually overlook the relations among target samples. This paper investigates into the intra-domain variations of the target domain and proposes a novel adaptation framework w.r.t three types of underlying invariance, i.e., Exemplar-Invariance, Camera-Invariance, and Neighborhood-Invariance. Specifically, an exemplar memory is introduced to store features of samples, which can effectively and efficiently enforce the invariance constraints over the global dataset. We further present the Graph-based Positive Prediction (GPP) method to explore reliable neighbors for the target domain, which is built upon the memory and is trained on the source samples. Experiments demonstrate that 1) the three invariance properties are complementary and indispensable for effective domain adaptation, 2) the memory plays a key role in implementing invariance learning and improves the performance with limited extra computation cost, 3) GPP can facilitate the invariance learning and thus significantly improves the results, and 4) our approach produces new state-of-the-art adaptation accuracy on three re-ID large-scale benchmarks.

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

http://hdl.handle.net/10453/157124