Support matching: A novel regularization to escape from mode collapse in GANs

Yao, Y; Pan, Y; Tsang, IW; Yao, X

Support matching: A novel regularization to escape from mode collapse in GANs

Yao, Y Pan, Y

Tsang, IW Yao, X

Permalink

Publisher:: Springer International Publishing
Publication Type:: Conference Proceeding
Citation:: Communications in Computer and Information Science, 2019, 1142 CCIS, pp. 40-48
Issue Date:: 2019-01-01

Closed Access

	Filename	Description	Size
	Support Matching.pdf	Published version	1.68 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	Yao, Y
dc.contributor.author	Pan, Y https://orcid.org/0000-0002-7950-4900
dc.contributor.author	Tsang, IW
dc.contributor.author	Yao, X
dc.date.accessioned	2021-07-30T08:00:20Z
dc.date.available	2021-07-30T08:00:20Z
dc.date.issued	2019-01-01
dc.identifier.citation	Communications in Computer and Information Science, 2019, 1142 CCIS, pp. 40-48
dc.identifier.isbn	9783030368074
dc.identifier.issn	1865-0929
dc.identifier.issn	1865-0937
dc.identifier.uri	http://hdl.handle.net/10453/150007
dc.description.abstract	Generative adversarial network (GAN) is an implicit generative model known for its ability to generate sharp images. However, it is poor at generating diverse data, which refers to the mode collapse problem. It turns out that GAN is prone to emphasizing the quality of samples but ignoring their diversity. When mode collapse happens, the support of the generated data distribution is not aligned with that of the real data distribution. We thus propose Support Regularized-GAN (SR-GAN) to address such a mode collapse issue by matching their support. Our experiments on synthetic and real-world datasets show that our regularization can mitigate the mode collapse and also improve the data quality.
dc.language	en
dc.publisher	Springer International Publishing
dc.relation	http://purl.org/au-research/grants/arc/LP150100671
dc.relation	http://purl.org/au-research/grants/arc/DP180100106
dc.relation	http://purl.org/au-research/grants/arc/DP200101328
dc.relation.ispartof	Communications in Computer and Information Science
dc.relation.isbasedon	10.1007/978-3-030-36808-1_5
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Support matching: A novel regularization to escape from mode collapse in GANs
dc.type	Conference Proceeding
utslib.citation.volume	1142 CCIS
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	*
dc.date.updated	2021-07-30T08:00:18Z
pubs.publication-status	Published
pubs.volume	1142 CCIS

Abstract:

Generative adversarial network (GAN) is an implicit generative model known for its ability to generate sharp images. However, it is poor at generating diverse data, which refers to the mode collapse problem. It turns out that GAN is prone to emphasizing the quality of samples but ignoring their diversity. When mode collapse happens, the support of the generated data distribution is not aligned with that of the real data distribution. We thus propose Support Regularized-GAN (SR-GAN) to address such a mode collapse issue by matching their support. Our experiments on synthetic and real-world datasets show that our regularization can mitigate the mode collapse and also improve the data quality.

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

http://hdl.handle.net/10453/150007