Unconstrained fuzzy feature fusion for heterogeneous unsupervised domain adaptation

Liu, F; Zhang, G; Lu, J

Unconstrained fuzzy feature fusion for heterogeneous unsupervised domain adaptation

Liu, F

Zhang, G

Lu, J

Permalink

Publication Type:: Conference Proceeding
Citation:: IEEE International Conference on Fuzzy Systems, 2018, 2018-July
Issue Date:: 2018-10-12

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted ManuscriptAdobe PDF (489.28 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Liu, F https://orcid.org/0000-0002-5005-9129	en_US
dc.contributor.author	Zhang, G https://orcid.org/0000-0003-3960-0583	en_US
dc.contributor.author	Lu, J https://orcid.org/0000-0003-0690-4732	en_US
dc.date.available	2020-08-01T19:06:27Z
dc.date.issued	2018-10-12	en_US
dc.identifier.citation	IEEE International Conference on Fuzzy Systems, 2018, 2018-July	en_US
dc.identifier.isbn	9781509060207	en_US
dc.identifier.issn	1098-7584	en_US
dc.identifier.uri	http://hdl.handle.net/10453/128637
dc.description.abstract	© 2018 IEEE. Domain adaptation can transfer knowledge from the source domain to improve pattern recognition accuracy in the target domain. However, it is rarely discussed when the target domain is unlabeled and heterogeneous with the source domain, which is a very challenging problem in the domain adaptation field. This paper presents a new feature reconstruction method: unconstrained fuzzy feature fusion. Through the reconstructed features of a source and a target domain, a geodesic flow kernel is applied to transfer knowledge between them. Furthermore, the original information of the target domain is also preserved when reconstructing the features of the two domains. Compared to the previous work, this work has two advantages: 1) the sum of the memberships of the original features to fuzzy features no longer must be one, and 2) the original information of the target domain is persevered. As a result of these advantages, this work delivers a better performance than previous studies using two public datasets.	en_US
dc.relation	http://purl.org/au-research/grants/arc/DP170101632
dc.relation.ispartof	IEEE International Conference on Fuzzy Systems	en_US
dc.relation.isbasedon	10.1109/FUZZ-IEEE.2018.8491633	en_US
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Unconstrained fuzzy feature fusion for heterogeneous unsupervised domain adaptation	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2018-July	en_US
utslib.for	0805 Distributed Computing	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	open_access	*
pubs.publication-status	Published	en_US
pubs.volume	2018-July	en_US

Abstract:

© 2018 IEEE. Domain adaptation can transfer knowledge from the source domain to improve pattern recognition accuracy in the target domain. However, it is rarely discussed when the target domain is unlabeled and heterogeneous with the source domain, which is a very challenging problem in the domain adaptation field. This paper presents a new feature reconstruction method: unconstrained fuzzy feature fusion. Through the reconstructed features of a source and a target domain, a geodesic flow kernel is applied to transfer knowledge between them. Furthermore, the original information of the target domain is also preserved when reconstructing the features of the two domains. Compared to the previous work, this work has two advantages: 1) the sum of the memberships of the original features to fuzzy features no longer must be one, and 2) the original information of the target domain is persevered. As a result of these advantages, this work delivers a better performance than previous studies using two public datasets.

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

http://hdl.handle.net/10453/128637