Virtual adversarial training in feature space to improve unsupervised video domain adaptation

Gorpincenko, Artjoms, French, Geoffrey and Mackiewicz, Michal ORCID: https://orcid.org/0000-0002-8777-8880 (2021) Virtual adversarial training in feature space to improve unsupervised video domain adaptation. Electronic Imaging, 2021 (10). 258-1-258-6. ISSN 2470-1173

[thumbnail of Accepted_Manuscript]
Preview
PDF (Accepted_Manuscript) - Accepted Version
Download (8MB) | Preview

Abstract

Virtual Adversarial Training has recently seen a lot of success in semi-supervised learning, as well as unsupervised Domain Adaptation. However, so far it has been used on input samples in the pixel space, whereas we propose to apply it directly to feature vectors. We also discuss the unstable behaviour of entropy minimization and Decision-Boundary Iterative Refinement Training With a Teacher in Domain Adaptation, and suggest substitutes that achieve similar behaviour. By adding the aforementioned techniques to the state of the art model TA3N, we either maintain competitive results or outperform prior art in multiple unsupervised video Domain Adaptation tasks.

Item Type: Article
Uncontrolled Keywords: computer graphics and computer-aided design,computer science applications,human-computer interaction,software,electrical and electronic engineering,atomic and molecular physics, and optics ,/dk/atira/pure/subjectarea/asjc/1700/1704
Faculty \ School: Faculty of Science > School of Computing Sciences
UEA Research Groups: Faculty of Science > Research Groups > Collaborative Centre for Sustainable Use of the Seas
Faculty of Science > Research Groups > Colour and Imaging Lab
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 24 Sep 2021 01:05
Last Modified: 20 Jun 2024 00:49
URI: https://ueaeprints.uea.ac.uk/id/eprint/81506
DOI: 10.2352/ISSN.2470-1173.2021.10.IPAS-258

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item