Regularized Deep Belief Network for Image Attribute Detection

Wu, F; Wang, Z; Lu, W; Li, X; Yang, Y; Luo, J; Zhuang, Y

Regularized Deep Belief Network for Image Attribute Detection

Wu, F Wang, Z Lu, W Li, X Yang, Y

Luo, J Zhuang, Y

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27 (7), pp. 1464 - 1477
Issue Date:: 2017-07-01

Closed Access

	Filename	Description	Size
	07428944.pdf	Published Version	2.76 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	Wu, F	en_US
dc.contributor.author	Wang, Z	en_US
dc.contributor.author	Lu, W	en_US
dc.contributor.author	Li, X	en_US
dc.contributor.author	Yang, Y https://orcid.org/0000-0001-5528-0546	en_US
dc.contributor.author	Luo, J	en_US
dc.contributor.author	Zhuang, Y	en_US
dc.date.issued	2017-07-01	en_US
dc.identifier.citation	IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27 (7), pp. 1464 - 1477	en_US
dc.identifier.issn	1051-8215	en_US
dc.identifier.uri	http://hdl.handle.net/10453/124719
dc.description.abstract	© 1991-2012 IEEE. In general, an image attribute is a human-nameable visual property that has a semantic connotation. Appropriate modeling of the intrinsic contextual correlations among attributes plays a fundamental role in attribute detection. In this paper, we consider image attribute detection from the perspective of regularized deep learning. In particular, we propose a regularized deep belief network (rDBN) to perform the image attribute detection task, which is composed of two parts: 1) a detection DBN (dDBN) that models the joint distribution of images and their corresponding attributes, which acts as an attribute detector and 2) a contextual restricted Boltzmann machine that explicitly models the correlations among attributes acting as a regularizer that restraints the output detection result given by the dDBN to meet the contextual prior of attributes. Furthermore, we propose an efficient fine-tuning scheme that can further optimize the performance of the dDBN by backpropagation. Experimental results show that the proposed rDBN obtains improvements over the state-of-the-art methods for attribute detection on the benchmark data sets.	en_US
dc.relation.ispartof	IEEE Transactions on Circuits and Systems for Video Technology	en_US
dc.relation.isbasedon	10.1109/TCSVT.2016.2539604	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Regularized Deep Belief Network for Image Attribute Detection	en_US
dc.type	Journal Article
utslib.citation.volume	7	en_US
utslib.citation.volume	27	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	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/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.issue	7	en_US
pubs.publication-status	Published	en_US
pubs.volume	27	en_US

Abstract:

© 1991-2012 IEEE. In general, an image attribute is a human-nameable visual property that has a semantic connotation. Appropriate modeling of the intrinsic contextual correlations among attributes plays a fundamental role in attribute detection. In this paper, we consider image attribute detection from the perspective of regularized deep learning. In particular, we propose a regularized deep belief network (rDBN) to perform the image attribute detection task, which is composed of two parts: 1) a detection DBN (dDBN) that models the joint distribution of images and their corresponding attributes, which acts as an attribute detector and 2) a contextual restricted Boltzmann machine that explicitly models the correlations among attributes acting as a regularizer that restraints the output detection result given by the dDBN to meet the contextual prior of attributes. Furthermore, we propose an efficient fine-tuning scheme that can further optimize the performance of the dDBN by backpropagation. Experimental results show that the proposed rDBN obtains improvements over the state-of-the-art methods for attribute detection on the benchmark data sets.

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

http://hdl.handle.net/10453/124719