A Probabilistic Code Balance Constraint with Compactness and Informativeness Enhancement for Deep Supervised Hashing

Zhang, Q; Hu, L; Cao, L; Shi, C; Wang, S; Liu, DD

A Probabilistic Code Balance Constraint with Compactness and Informativeness Enhancement for Deep Supervised Hashing

Zhang, Q Hu, L Cao, L Shi, C Wang, S

Liu, DD

Permalink

Publisher:: International Joint Conferences on Artificial Intelligence Organization
Publication Type:: Conference Proceeding
Citation:: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022, pp. 1651-1657
Issue Date:: 2022-07-01

Recently Added

	Filename	Description	Size
	43. IJCAI. 2022. Qi.pdf	Published version	342.59 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is new to OPUS and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, Q
dc.contributor.author	Hu, L
dc.contributor.author	Cao, L
dc.contributor.author	Shi, C
dc.contributor.author	Wang, S https://orcid.org/0000-0003-1133-9379
dc.contributor.author	Liu, DD
dc.date	2022-07-23
dc.date.accessioned	2022-09-06T04:36:09Z
dc.date.available	2022-09-06T04:36:09Z
dc.date.issued	2022-07-01
dc.identifier.citation	Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022, pp. 1651-1657
dc.identifier.uri	http://hdl.handle.net/10453/161427
dc.description.abstract	<jats:p>Building on deep representation learning, deep supervised hashing has achieved promising performance in tasks like similarity retrieval. However, conventional code balance constraints (i.e., bit balance and bit uncorrelation) imposed on avoiding overfitting and improving hash code quality are unsuitable for deep supervised hashing owing to their inefficiency and impracticality of simultaneously learning deep data representations and hash functions. To address this issue, we propose probabilistic code balance constraints on deep supervised hashing to force each hash code to conform to a discrete uniform distribution. Accordingly, a Wasserstein regularizer aligns the distribution of generated hash codes to a uniform distribution. Theoretical analyses reveal that the proposed constraints form a general deep hashing framework for both bit balance and bit uncorrelation and maximizing the mutual information between data input and their corresponding hash codes. Extensive empirical analyses on two benchmark datasets further demonstrate the enhancement of compactness and informativeness of hash codes for deep supervised hash to improve retrieval performance (code available at: https://github.com/mumuxi/dshwr).</jats:p>
dc.language	en
dc.publisher	International Joint Conferences on Artificial Intelligence Organization
dc.relation.ispartof	Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
dc.relation.ispartof	Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
dc.relation.isbasedon	10.24963/ijcai.2022/230
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.title	A Probabilistic Code Balance Constraint with Compactness and Informativeness Enhancement for Deep Supervised Hashing
dc.type	Conference Proceeding
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	recently_added	*
dc.date.updated	2022-09-06T04:36:07Z
pubs.finish-date	2022-07-29
pubs.publication-status	Published
pubs.start-date	2022-07-23

Abstract:

Building on deep representation learning, deep supervised hashing has achieved promising performance in tasks like similarity retrieval. However, conventional code balance constraints (i.e., bit balance and bit uncorrelation) imposed on avoiding overfitting and improving hash code quality are unsuitable for deep supervised hashing owing to their inefficiency and impracticality of simultaneously learning deep data representations and hash functions. To address this issue, we propose probabilistic code balance constraints on deep supervised hashing to force each hash code to conform to a discrete uniform distribution. Accordingly, a Wasserstein regularizer aligns the distribution of generated hash codes to a uniform distribution. Theoretical analyses reveal that the proposed constraints form a general deep hashing framework for both bit balance and bit uncorrelation and maximizing the mutual information between data input and their corresponding hash codes. Extensive empirical analyses on two benchmark datasets further demonstrate the enhancement of compactness and informativeness of hash codes for deep supervised hash to improve retrieval performance (code available at: https://github.com/mumuxi/dshwr).

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

http://hdl.handle.net/10453/161427