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 …

Test-time adaptation (TTA) aims to address the distribution shift between the training and
test data with only unlabeled data at test time. Existing TTA methods often focus on …

Abstract Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source
model to continually changing unsupervised target domains. In this paper, we systematically …

Test-time adaptation (TTA) has emerged as a viable solution to adapt pre-trained models to
domain shifts using unlabeled test data. However TTA faces challenges of adaptation …

Test-time adaptation (TTA) aims at adapting a model pre-trained on the labeled source
domain to the unlabeled target domain. Existing methods usually focus on improving TTA …

Current test-time adaptation (TTA) approaches aim to adapt a machine learning model to
environments that change continuously. Yet, it is unclear whether TTA methods can maintain …

Adapting a trained model to perform satisfactorily on continually changing test environments
is an important and challenging task. In this work, we propose a novel framework, SANTA …

Machine learning algorithms have achieved remarkable success across various disciplines,
use cases and applications, under the prevailing assumption that training and test samples …

Distribution shifts between training and test data are all but inevitable over the lifecycle of a
deployed model and lead to performance decay. Adapting the model can hopefully mitigate …