Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

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 …

We present a novel approach for test-time adaptation via online self-training, consisting of
two components. First, we introduce a statistical framework that detects distribution shifts in …

Large pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated
excellent zero-shot generalizability across various downstream tasks. However, recent …