Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?. (arXiv:2305.18712v2 [cs.CV] UPDATED)

Unsupervised domain adaptation (UDA) involves adapting a model trained on a
label-rich source domain to an unlabeled target domain. However, in real-world
scenarios, the absence of target-domain labels makes it challenging to evaluate
the performance of UDA models. Furthermore, prevailing UDA methods relying on
adversarial training and self-training could lead to model degeneration and
negative transfer, further exacerbating the evaluation problem. In this paper,
we propose a novel metric called the \textit{Transfer Score} to address these
issues. The proposed metric …

adversarial adversarial training arxiv cs.cv domain domain adaptation labels performance self-training training unsupervised world