The Entropy Enigma: Success and Failure of Entropy Minimization

arXiv:2405.05012v1 Announce Type: new
Abstract: Entropy minimization (EM) is frequently used to increase the accuracy of classification models when they're faced with new data at test time. EM is a self-supervised learning method that optimizes classifiers to assign even higher probabilities to their top predicted classes. In this paper, we analyze why EM works when adapting a model for a few steps and why it eventually fails after adapting for many steps. We show that, at first, EM causes the …

arxiv cs.cv entropy failure success type