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

Research output: Contribution to journalArticlepeer-review

1 Downloads (Pure)

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.
Original languageEnglish
Article number258
Pages (from-to)258-1-258-6
Number of pages6
JournalElectronic Imaging
Volume2021
Issue number10
DOIs
Publication statusPublished - 18 Jan 2021

Cite this