Domain Gap Estimation for Source Free Unsupervised Domain Adaptation with Many Classifiers. (arXiv:2207.05785v1 [cs.CV])

In theory, the success of unsupervised domain adaptation (UDA) largely relies
on domain gap estimation. However, for source free UDA, the source domain data
can not be accessed during adaptation, which poses great challenge of measuring
the domain gap. In this paper, we propose to use many classifiers to learn the
source domain decision boundaries, which provides a tighter upper bound of the
domain gap, even if both of the domain data can not be simultaneously accessed.
The source model …

arxiv classifiers cv domain adaptation free gap unsupervised