Domain adaptation on the statistical manifold

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

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

101 Citations (Scopus)

Abstract

In this paper, we tackle the problem of unsupervised domain adaptation for classification. In the unsupervised scenario where no labeled samples from the target domain are provided, a popular approach consists in transforming the data such that the source and target distributions become similar. To compare the two distributions, existing approaches make use of the Maximum Mean Discrepancy (MMD). However, this does not exploit the fact that probability distributions lie on a Riemannian manifold. Here, we propose to make better use of the structure of this manifold and rely on the distance on the manifold to compare the source and target distributions. In this framework, we introduce a sample selection method and a subspace-based method for unsupervised domain adaptation, and show that both these manifold-based techniques outperform the corresponding approaches based on the MMD. Furthermore, we show that our subspace-based approach yields state-of-the-art results on a standard object recognition benchmark.

Original languageEnglish
Title of host publicationProceedings - 2014 IEEE Conference on Computer Vision and Pattern Recognition
EditorsRonen Basri, Cornelia Fermuller, Aleix Martinez, René Vidal
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages2481-2488
Number of pages8
ISBN (Electronic)9781479951178
DOIs
Publication statusPublished - 2014
Externally publishedYes
EventIEEE Conference on Computer Vision and Pattern Recognition 2014 - Columbus, United States of America
Duration: 23 Jun 201428 Jun 2014
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6909096 (IEEE Conference Proceedings)

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition 2014
Abbreviated titleCVPR 2014
Country/TerritoryUnited States of America
CityColumbus
Period23/06/1428/06/14
Internet address

Keywords

  • Domain Adaptation
  • Object Recognition
  • Statistical Manifold

Cite this