Unsupervised domain adaptation by domain invariant projection

Mahsa Baktashmotlagh, Mehrtash T. Harandi, Brian C. Lovell, Mathieu Salzmann

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

364 Citations (Scopus)

Abstract

Domain-invariant representations are key to addressing the domain shift problem where the training and test examples follow different distributions. Existing techniques that have attempted to match the distributions of the source and target domains typically compare these distributions in the original feature space. This space, however, may not be directly suitable for such a comparison, since some of the features may have been distorted by the domain shift, or may be domain specific. In this paper, we introduce a Domain Invariant Projection approach: An unsupervised domain adaptation method that overcomes this issue by extracting the information that is invariant across the source and target domains. More specifically, we learn a projection of the data to a low-dimensional latent space where the distance between the empirical distributions of the source and target examples is minimized. We demonstrate the effectiveness of our approach on the task of visual object recognition and show that it outperforms state-of-the-art methods on a standard domain adaptation benchmark dataset.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages769-776
Number of pages8
ISBN (Print)9781479928392
DOIs
Publication statusPublished - 1 Jan 2013
Externally publishedYes
EventIEEE International Conference on Computer Vision 2013 - Sydney Convention and Exhibition Centre, Sydney, Australia
Duration: 1 Dec 20138 Dec 2013
Conference number: 14th
http://www.iccv2013.org/
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6750807 (IEEE Conference Proceedings)

Publication series

NameProceedings of the IEEE International Conference on Computer Vision

Conference

ConferenceIEEE International Conference on Computer Vision 2013
Abbreviated titleICCV 2013
Country/TerritoryAustralia
CitySydney
Period1/12/138/12/13
Internet address

Cite this