Generated Data with Sparse Regularized Multi-Pseudo Label for Person Re-Identification

Huang, L; Yang, Q; Wu, J; Huang, Y; Wu, Q; Xu, J

Generated Data with Sparse Regularized Multi-Pseudo Label for Person Re-Identification

Huang, L Yang, Q Wu, J Huang, Y

Wu, Q Xu, J

Permalink

Publication Type:: Journal Article
Citation:: IEEE Signal Processing Letters, 2020, 27 pp. 391 - 395
Issue Date:: 2020-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

The embargo period expires on 1 Jan 2022

Adobe PDF

Download Accepted ManuscriptAdobe PDF (424.16 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Huang, L	en_US
dc.contributor.author	Yang, Q	en_US
dc.contributor.author	Wu, J	en_US
dc.contributor.author	Huang, Y https://orcid.org/0000-0002-1363-5318	en_US
dc.contributor.author	Wu, Q	en_US
dc.contributor.author	Xu, J https://orcid.org/0000-0002-9102-3616	en_US
dc.date.accessioned	2020-04-01T02:05:00Z
dc.date.available	2020-04-01T02:05:00Z
dc.date.issued	2020-01-01	en_US
dc.identifier.citation	IEEE Signal Processing Letters, 2020, 27 pp. 391 - 395	en_US
dc.identifier.issn	1070-9908	en_US
dc.identifier.uri	http://hdl.handle.net/10453/139685
dc.description.abstract	© 1994-2012 IEEE. Recently, Generative Adversarial Network (GAN) has been adopted to improve person re-identification (person re-ID) performance through data augmentation. However, directly leveraging generated data to train a re-ID model may easily lead to over-fitting issue on these extra data and decrease the generalisability of model to learn true ID-related features from real data. Inspired by the previous approach which assigns multi-pseudo labels on the generated data to reduce the risk of over-fitting, we propose to take sparse regularization into consideration. We attempt to further improve the performance of current re-ID models by using the unlabeled generated data. The proposed Sparse Regularized Multi-Pseudo Label (SRMpL) can effectively prevent the over-fitting issue when some larger weights are assigned to the generated data. Our experiments are carried out on two publicly available person re-ID datasets (e.g., Market-1501 and DukeMTMC-reID). Compared with existing unlabeled generated data re-ID solutions, our approach achieves competitive performance. Two classical re-ID models are used to verify our sparse regularization label on generated data, i.e., an ID-embedding network and a two-stream network.	en_US
dc.relation.ispartof	IEEE Signal Processing Letters	en_US
dc.relation.isbasedon	10.1109/LSP.2020.2972768	en_US
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject.classification	Networking & Telecommunications	en_US
dc.title	Generated Data with Sparse Regularized Multi-Pseudo Label for Person Re-Identification	en_US
dc.type	Journal Article
utslib.citation.volume	27	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	1005 Communications Technologies	en_US
pubs.embargo.period	Not known	en_US
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/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
pubs.organisational-group	/University of Technology Sydney/Students
utslib.copyright.status	open_access	*
utslib.copyright.embargo	2022-01-01T00:00:00+1100
pubs.publication-status	Published	en_US
pubs.volume	27	en_US

Abstract:

© 1994-2012 IEEE. Recently, Generative Adversarial Network (GAN) has been adopted to improve person re-identification (person re-ID) performance through data augmentation. However, directly leveraging generated data to train a re-ID model may easily lead to over-fitting issue on these extra data and decrease the generalisability of model to learn true ID-related features from real data. Inspired by the previous approach which assigns multi-pseudo labels on the generated data to reduce the risk of over-fitting, we propose to take sparse regularization into consideration. We attempt to further improve the performance of current re-ID models by using the unlabeled generated data. The proposed Sparse Regularized Multi-Pseudo Label (SRMpL) can effectively prevent the over-fitting issue when some larger weights are assigned to the generated data. Our experiments are carried out on two publicly available person re-ID datasets (e.g., Market-1501 and DukeMTMC-reID). Compared with existing unlabeled generated data re-ID solutions, our approach achieves competitive performance. Two classical re-ID models are used to verify our sparse regularization label on generated data, i.e., an ID-embedding network and a two-stream network.

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

http://hdl.handle.net/10453/139685