Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?

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