Adversarially Masked Video Consistency for Unsupervised Domain Adaptation

arXiv:2403.16242v1 Announce Type: new
Abstract: We study the problem of unsupervised domain adaptation for egocentric videos. We propose a transformer-based model to learn class-discriminative and domain-invariant feature representations. It consists of two novel designs. The first module is called Generative Adversarial Domain Alignment Network with the aim of learning domain-invariant representations. It simultaneously learns a mask generator and a domain-invariant encoder in an adversarial way. The domain-invariant encoder is trained to minimize the distance between the source and target domain. …

abstract adversarial aim alignment arxiv class cs.cv designs domain domain adaptation feature generative learn network novel study transformer type unsupervised video videos