Back to articles
Articles
Volume: 33 | Article ID: art00012
Image
Virtual Adversarial Training in Feature Space to Improve Unsupervised Video Domain Adaptation
  DOI :  10.2352/ISSN.2470-1173.2021.10.IPAS-258  Published OnlineJanuary 2021
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.

Subject Areas :
Views 7
Downloads 0
 articleview.views 7
 articleview.downloads 0
  Cite this article 

Artjoms Gorpincenko, Geoffrey French, Michal Mackiewicz, "Virtual Adversarial Training in Feature Space to Improve Unsupervised Video Domain Adaptationin Proc. IS&T Int’l. Symp. on Electronic Imaging: Image Processing: Algorithms and Systems XIX,  2021,  pp 258-1 - 258-6,  https://doi.org/10.2352/ISSN.2470-1173.2021.10.IPAS-258

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2021
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology
IS&T 7003 Kilworth Lane Springfield, VA 22151 USA