Active Learning for Domain Adaptation: An Energy-Based Approach. (arXiv:2112.01406v3 [cs.LG] UPDATED)

Unsupervised domain adaptation has recently emerged as an effective paradigm
for generalizing deep neural networks to new target domains. However, there is
still enormous potential to be tapped to reach the fully supervised
performance. In this paper, we present a novel active learning strategy to
assist knowledge transfer in the target domain, dubbed active domain
adaptation. We start from an observation that energy-based models exhibit
\textit{free energy biases} when training (source) and test (target) data come
from different distributions. Inspired …

active learning arxiv domain adaptation energy learning