Dynamic Classifier Alignment for Unsupervised Multi-Source Domain Adaptation

Li, K; Lu, J; Zuo, H; Zhang, G

Dynamic Classifier Alignment for Unsupervised Multi-Source Domain Adaptation

Li, K Lu, J

Zuo, H

Zhang, G

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Journal Article
Citation:: IEEE Transactions on Knowledge and Data Engineering, 2022, PP, (99), pp. 1-1
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	Dynamic_Classifier_Alignment_for_Unsupervised_Multi-Source_Domain_Adaptation.pdf	Published version	5.35 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	Li, K
dc.contributor.author	Lu, J https://orcid.org/0000-0003-0690-4732
dc.contributor.author	Zuo, H https://orcid.org/0000-0002-9122-0775
dc.contributor.author	Zhang, G https://orcid.org/0000-0003-3960-0583
dc.date.accessioned	2023-03-23T00:57:34Z
dc.date.available	2023-03-23T00:57:34Z
dc.date.issued	2022-01-01
dc.identifier.citation	IEEE Transactions on Knowledge and Data Engineering, 2022, PP, (99), pp. 1-1
dc.identifier.issn	1041-4347
dc.identifier.issn	1558-2191
dc.identifier.uri	http://hdl.handle.net/10453/168126
dc.description.abstract	Unsupervised domain adaptation leverages the previously gained knowledge from a labeled source domain to tackle the task from a different but similar unlabeled target domain. Most existing methods focus on transferring knowledge from a single source domain, but the information from a single domain may be inadequate to complete the target task. Some previous studies have turned to multi-view representations to enrich the transferable information. However, they simply concatenate multi-view features, which may result in information redundancy. In this paper, we propose a dynamic classifier alignment (DCA) method for multi-source domain adaptation, which aligns classifiers driven from multi-view features via a sample-wise automatic way. As proposed, both the importance of each view and the contribution of each source domain are investigated. To determine the important degrees of multiple views, an importance learning function is built by generating an auxiliary classifier. To learn the source combination parameters, a domain discriminator is developed to estimate the probability of a sample belonging to multiple source domains. Meanwhile, a self-training strategy is proposed to enhance the cross-domain ability of source classifiers with the assistance of pseudo target labels. Experiments on real-world visual datasets show the superiority of the proposed DCA.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation	http://purl.org/au-research/grants/arc/FL190100149
dc.relation.ispartof	IEEE Transactions on Knowledge and Data Engineering
dc.relation.isbasedon	10.1109/TKDE.2022.3144423
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	08 Information and Computing Sciences
dc.subject.classification	Information Systems
dc.title	Dynamic Classifier Alignment for Unsupervised Multi-Source Domain Adaptation
dc.type	Journal Article
utslib.citation.volume	PP
utslib.for	08 Information and Computing Sciences
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
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2023-03-23T00:57:33Z
pubs.issue	99
pubs.publication-status	Published
pubs.volume	PP
utslib.citation.issue	99

Abstract:

Unsupervised domain adaptation leverages the previously gained knowledge from a labeled source domain to tackle the task from a different but similar unlabeled target domain. Most existing methods focus on transferring knowledge from a single source domain, but the information from a single domain may be inadequate to complete the target task. Some previous studies have turned to multi-view representations to enrich the transferable information. However, they simply concatenate multi-view features, which may result in information redundancy. In this paper, we propose a dynamic classifier alignment (DCA) method for multi-source domain adaptation, which aligns classifiers driven from multi-view features via a sample-wise automatic way. As proposed, both the importance of each view and the contribution of each source domain are investigated. To determine the important degrees of multiple views, an importance learning function is built by generating an auxiliary classifier. To learn the source combination parameters, a domain discriminator is developed to estimate the probability of a sample belonging to multiple source domains. Meanwhile, a self-training strategy is proposed to enhance the cross-domain ability of source classifiers with the assistance of pseudo target labels. Experiments on real-world visual datasets show the superiority of the proposed DCA.

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

http://hdl.handle.net/10453/168126