Unsupervised domain adaptation by domain invariant projection
-
Altmetric Citations
Baktashmotlagh, Mahsa; Harandi, Mehrtash; Lovell, Brian C; Salzmann, Mathieu
Description
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...[Show more]
dc.contributor.author | Baktashmotlagh, Mahsa | |
---|---|---|
dc.contributor.author | Harandi, Mehrtash | |
dc.contributor.author | Lovell, Brian C | |
dc.contributor.author | Salzmann, Mathieu | |
dc.coverage.spatial | Sydney Australia | |
dc.date.accessioned | 2015-12-10T23:10:01Z | |
dc.date.created | December 1-8 2013 | |
dc.identifier.isbn | 9781479930227 | |
dc.identifier.uri | http://hdl.handle.net/1885/63543 | |
dc.description.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. | |
dc.publisher | IEEE | |
dc.relation.ispartofseries | 2013 14th IEEE International Conference on Computer Vision Workshops, ICCVW 2013 | |
dc.source | Proceedings of the IEEE International Conference on Computer Vision | |
dc.title | Unsupervised domain adaptation by domain invariant projection | |
dc.type | Conference paper | |
local.description.notes | Imported from ARIES | |
local.description.refereed | Yes | |
dc.date.issued | 2013 | |
local.identifier.absfor | 080104 - Computer Vision | |
local.identifier.ariespublication | U3488905xPUB819 | |
local.type.status | Published Version | |
local.contributor.affiliation | Baktashmotlagh, Mahsa, University of Queensland | |
local.contributor.affiliation | Harandi, Mehrtash, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Lovell, Brian C, University of Queensland | |
local.contributor.affiliation | Salzmann, Mathieu, College of Engineering and Computer Science, ANU | |
local.description.embargo | 2037-12-31 | |
local.bibliographicCitation.startpage | 769 | |
local.bibliographicCitation.lastpage | 776 | |
local.identifier.doi | 10.1109/ICCV.2013.100 | |
local.identifier.absseo | 970108 - Expanding Knowledge in the Information and Computing Sciences | |
dc.date.updated | 2015-12-10T09:16:03Z | |
local.identifier.scopusID | 2-s2.0-84898798212 | |
Collections | ANU Research Publications |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
01_Baktashmotlagh_Unsupervised_domain_adaptation_2013.pdf | 381.63 kB | Adobe PDF | Request a copy |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator