GAN2C: Information Completion GAN with Dual Consistency Constraints

Zhang, L; Li, J; Huang, T; Ma, Z; Lin, Z; Prasad, M

GAN2C: Information Completion GAN with Dual Consistency Constraints

Zhang, L Li, J

Huang, T Ma, Z Lin, Z Prasad, M

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings of the International Joint Conference on Neural Networks, 2018, 2018-July
Issue Date:: 2018-10-10

Closed Access

	Filename	Description	Size
	08489550.pdf	Published version	657.08 kB	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	Zhang, L	en_US
dc.contributor.author	Li, J https://orcid.org/0000-0002-1336-2241	en_US
dc.contributor.author	Huang, T	en_US
dc.contributor.author	Ma, Z	en_US
dc.contributor.author	Lin, Z	en_US
dc.contributor.author	Prasad, M https://orcid.org/0000-0001-9719-2253	en_US
dc.date.issued	2018-10-10	en_US
dc.identifier.citation	Proceedings of the International Joint Conference on Neural Networks, 2018, 2018-July	en_US
dc.identifier.isbn	9781509060146	en_US
dc.identifier.uri	http://hdl.handle.net/10453/132461
dc.description.abstract	© 2018 IEEE. This paper proposes an information completion technique, GAN2C, by imposing dual consistency constraints (2C) to a closed loop encoder-decoder architecture based on the generative adversarial nets (GAN). When adopting deep neural networks as function approximators, GAN2C enables highly effective multi-modality image conversion with sparse observation in the target modes. For empirical demonstration and model evaluation, we show that trained deep neural networks in GAN2C can infer colors for grayscale images, as well as estimate rich 3D information of a scene by densely predicting the depths. The results of the experiments show that in both tasks GAN2C as a generic framework has been comparable to or advanced the state-of-the-art performance which are achieved by highly specialized systems. Code is available at https://github.com/AdalinZhang/GAN2C.	en_US
dc.relation.ispartof	Proceedings of the International Joint Conference on Neural Networks	en_US
dc.relation.isbasedon	10.1109/IJCNN.2018.8489550	en_US
dc.title	GAN2C: Information Completion GAN with Dual Consistency Constraints	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2018-July	en_US
utslib.for	0803 Computer Software	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 Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	2018-July	en_US

Abstract:

© 2018 IEEE. This paper proposes an information completion technique, GAN2C, by imposing dual consistency constraints (2C) to a closed loop encoder-decoder architecture based on the generative adversarial nets (GAN). When adopting deep neural networks as function approximators, GAN2C enables highly effective multi-modality image conversion with sparse observation in the target modes. For empirical demonstration and model evaluation, we show that trained deep neural networks in GAN2C can infer colors for grayscale images, as well as estimate rich 3D information of a scene by densely predicting the depths. The results of the experiments show that in both tasks GAN2C as a generic framework has been comparable to or advanced the state-of-the-art performance which are achieved by highly specialized systems. Code is available at https://github.com/AdalinZhang/GAN2C.

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

http://hdl.handle.net/10453/132461