Virtual Adversarial Training in Feature Space to Improve Unsupervised Video Domain Adaptation

08/19/2020 ∙ by Artjoms Gorpincenko, et al. ∙ 0

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 TA^3N, we either maintain competitive results or outperform prior art in multiple unsupervised video Domain Adaptation tasks



There are no comments yet.


page 3

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.