Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox. (arXiv:2207.04494v1 [cs.CV] CROSS LISTED)

Universal domain adaptation (UniDA) is a general unsupervised domain
adaptation setting, which addresses both domain and label shifts in adaptation.
Its main challenge lies in how to identify target samples in unshared or
unknown classes. Previous methods commonly strive to depict sample "confidence"
along with a threshold for rejecting unknowns, and align feature distributions
of shared classes across domains. However, it is still hard to pre-specify a
"confidence" criterion and threshold which are adaptive to various real tasks,
and a …

arxiv authentication cv domain adaptation paradox