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 language | English |
---|---|
Title of host publication | Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013 |
Publisher | IEEE, Institute of Electrical and Electronics Engineers |
Pages | 769-776 |
Number of pages | 8 |
ISBN (Print) | 9781479928392 |
DOIs | |
Publication status | Published - 1 Jan 2013 |
Externally published | Yes |
Event | IEEE International Conference on Computer Vision 2013 - Sydney Convention and Exhibition Centre, Sydney, Australia Duration: 1 Dec 2013 → 8 Dec 2013 Conference number: 14th http://www.iccv2013.org/ http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6750807 (IEEE Conference Proceedings) |
Publication series
Name | Proceedings of the IEEE International Conference on Computer Vision |
---|
Conference
Conference | IEEE International Conference on Computer Vision 2013 |
---|---|
Abbreviated title | ICCV 2013 |
Country/Territory | Australia |
City | Sydney |
Period | 1/12/13 → 8/12/13 |
Internet address |
|