TTSR: Tensor-Train Subspace Representation Method for Visual Domain Adaptation

Li, G; Xu, P; Peng, S; Wang, C; Cai, Y; Yu, S

TTSR: Tensor-Train Subspace Representation Method for Visual Domain Adaptation

Li, G Xu, P Peng, S Wang, C Cai, Y Yu, S

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Journal Article
Citation:: IEEE Transactions on Knowledge and Data Engineering, 2024, PP, (99), pp. 1-14
Issue Date:: 2024-01-01

Closed Access

	Filename	Description	Size
	1723976.pdf	Published version	8.82 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	Li, G
dc.contributor.author	Xu, P
dc.contributor.author	Peng, S
dc.contributor.author	Wang, C
dc.contributor.author	Cai, Y
dc.contributor.author	Yu, S https://orcid.org/0000-0003-4485-6743
dc.date.accessioned	2024-08-21T05:44:26Z
dc.date.available	2024-08-21T05:44:26Z
dc.date.issued	2024-01-01
dc.identifier.citation	IEEE Transactions on Knowledge and Data Engineering, 2024, PP, (99), pp. 1-14
dc.identifier.issn	1041-4347
dc.identifier.issn	1558-2191
dc.identifier.uri	http://hdl.handle.net/10453/180510
dc.description.abstract	Most existing methods for visual domain adaptation need to convert high-order tensors into one-order high-dimensional vectors through naive vectorization operations. However, they not only destroy the internal spatial structure within the original high-order tensors, but also result in exponentially increasing model parameters. To address these problems, we propose a novel method for visual domain adaptation by representing tensorial features in tensor-train subspace in this paper. Specifically, we firstly provide a theoretical deduction by constructing a tensor-train subspace and proving its linearity and left-orthogonality. Secondly, to extract common tensorial features between source and target domains, we formulate the visual domain adaptation problem into an optimization problem that models the aforementioned common tensor-train subspace between two domains, as well as their corresponding projections. Thirdly, we design a tensor-train subspace representation algorithm (TTSR) to solve the multiple variables optimization problem by optimizing its sub-problems iteratively, so as to process high-order tensorial features. Finally, we evaluate the performance of our proposed TTSR algorithm by conducting extensive experiments on three popular public datasets. The experimental results demonstrate that the TTSR algorithm can improve the classification accuracy of unlabeled target domain than that of baseline algorithms.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	IEEE Transactions on Knowledge and Data Engineering
dc.relation.isbasedon	10.1109/TKDE.2024.3391019
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	08 Information and Computing Sciences
dc.subject.classification	Information Systems
dc.subject.classification	46 Information and computing sciences
dc.title	TTSR: Tensor-Train Subspace Representation Method for Visual Domain Adaptation
dc.type	Journal Article
utslib.citation.volume	PP
utslib.for	08 Information and Computing Sciences
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 - CCSP - Centre for Cyber Security and Privacy
pubs.organisational-group	University of Technology Sydney/All Manual Groups
pubs.organisational-group	University of Technology Sydney/All Manual Groups/Centre for Cyber Security and Privacy (CCSP)
utslib.copyright.status	closed_access	*
dc.date.updated	2024-08-21T05:44:18Z
pubs.issue	99
pubs.publication-status	Published
pubs.volume	PP
utslib.citation.issue	99

Abstract:

Most existing methods for visual domain adaptation need to convert high-order tensors into one-order high-dimensional vectors through naive vectorization operations. However, they not only destroy the internal spatial structure within the original high-order tensors, but also result in exponentially increasing model parameters. To address these problems, we propose a novel method for visual domain adaptation by representing tensorial features in tensor-train subspace in this paper. Specifically, we firstly provide a theoretical deduction by constructing a tensor-train subspace and proving its linearity and left-orthogonality. Secondly, to extract common tensorial features between source and target domains, we formulate the visual domain adaptation problem into an optimization problem that models the aforementioned common tensor-train subspace between two domains, as well as their corresponding projections. Thirdly, we design a tensor-train subspace representation algorithm (TTSR) to solve the multiple variables optimization problem by optimizing its sub-problems iteratively, so as to process high-order tensorial features. Finally, we evaluate the performance of our proposed TTSR algorithm by conducting extensive experiments on three popular public datasets. The experimental results demonstrate that the TTSR algorithm can improve the classification accuracy of unlabeled target domain than that of baseline algorithms.

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

http://hdl.handle.net/10453/180510