Balancing Discriminability and Transferability for Source-Free Domain Adaptation. (arXiv:2206.08009v1 [cs.CV])

Web: http://arxiv.org/abs/2206.08009

Conventional domain adaptation (DA) techniques aim to improve domain
transferability by learning domain-invariant representations; while
concurrently preserving the task-discriminability knowledge gathered from the
labeled source data. However, the requirement of simultaneous access to labeled
source and unlabeled target renders them unsuitable for the challenging
source-free DA setting. The trivial solution of realizing an effective original
to generic domain mapping improves transferability but degrades task
discriminability. Upon analyzing the hurdles from both theoretical and
empirical standpoints, we derive novel insights to …

arxiv cv domain adaptation free