Domain Consensus Clustering for Universal Domain Adaptation

Li, G; Kang, G; Zhu, Y; Wei, Y; Yang, Y

Domain Consensus Clustering for Universal Domain Adaptation

Li, G Kang, G Zhu, Y Wei, Y Yang, Y

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, 00, pp. 9752-9761
Issue Date:: 2021-11-13

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted versionAdobe PDF (1.06 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Li, G
dc.contributor.author	Kang, G
dc.contributor.author	Zhu, Y
dc.contributor.author	Wei, Y
dc.contributor.author	Yang, Y https://orcid.org/0000-0002-0512-880X
dc.date	2021-06-20
dc.date.accessioned	2022-06-04T06:37:53Z
dc.date.available	2022-06-04T06:37:53Z
dc.date.issued	2021-11-13
dc.identifier.citation	2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, 00, pp. 9752-9761
dc.identifier.isbn	9781665445092
dc.identifier.issn	1063-6919
dc.identifier.uri	http://hdl.handle.net/10453/157923
dc.description.abstract	In this paper, we investigate Universal Domain Adaptation (UniDA) problem, which aims to transfer the knowledge from source to target under unaligned label space. The main challenge of UniDA lies in how to separate common classes (i.e., classes shared across domains), from private classes (i.e., classes only exist in one domain). Previous works treat the private samples in the target as one generic class but ignore their intrinsic structure. Consequently, the resulting representations are not compact enough in the latent space and can be easily confused with common samples. To better exploit the intrinsic structure of the target domain, we propose Domain Consensus Clustering (DCC), which exploits the domain consensus knowledge to discover discriminative clusters on both common samples and private ones. Specifically, we draw the domain consensus knowledge from two aspects to facilitate the clustering and the private class discovery, i.e., the semantic-level consensus, which identifies the cycle-consistent clusters as the common classes, and the sample-level consensus, which utilizes the cross-domain classification agreement to determine the number of clusters and discover the private classes. Based on DCC, we are able to separate the private classes from the common ones, and differentiate the private classes themselves. Finally, we apply a class-aware alignment technique on identified common samples to minimize the distribution shift, and a prototypical regularizer to inspire discriminative target clusters. Experiments on four benchmarks demonstrate DCC significantly outperforms previous state-of-the-arts.
dc.language	en
dc.publisher	IEEE
dc.relation	http://purl.org/au-research/grants/arc/DE190101315
dc.relation	http://purl.org/au-research/grants/arc/DP200100938
dc.relation.ispartof	2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
dc.relation.ispartof	2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition
dc.relation.ispartofseries	IEEE Conference on Computer Vision and Pattern Recognition
dc.relation.isbasedon	10.1109/cvpr46437.2021.00963
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Domain Consensus Clustering for Universal Domain Adaptation
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	Nashville, TN, USA
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	open_access	*
dc.date.updated	2022-06-04T06:37:52Z
pubs.finish-date	2021-06-25
pubs.publication-status	Published
pubs.start-date	2021-06-20
pubs.volume	00

Abstract:

In this paper, we investigate Universal Domain Adaptation (UniDA) problem, which aims to transfer the knowledge from source to target under unaligned label space. The main challenge of UniDA lies in how to separate common classes (i.e., classes shared across domains), from private classes (i.e., classes only exist in one domain). Previous works treat the private samples in the target as one generic class but ignore their intrinsic structure. Consequently, the resulting representations are not compact enough in the latent space and can be easily confused with common samples. To better exploit the intrinsic structure of the target domain, we propose Domain Consensus Clustering (DCC), which exploits the domain consensus knowledge to discover discriminative clusters on both common samples and private ones. Specifically, we draw the domain consensus knowledge from two aspects to facilitate the clustering and the private class discovery, i.e., the semantic-level consensus, which identifies the cycle-consistent clusters as the common classes, and the sample-level consensus, which utilizes the cross-domain classification agreement to determine the number of clusters and discover the private classes. Based on DCC, we are able to separate the private classes from the common ones, and differentiate the private classes themselves. Finally, we apply a class-aware alignment technique on identified common samples to minimize the distribution shift, and a prototypical regularizer to inspire discriminative target clusters. Experiments on four benchmarks demonstrate DCC significantly outperforms previous state-of-the-arts.

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

http://hdl.handle.net/10453/157923