A comprehensive survey on test-time adaptation under distribution shifts

J Liang, R He, T Tan - International Journal of Computer Vision, 2025 - Springer
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 …

The entropy enigma: Success and failure of entropy minimization

O Press, R Shwartz-Ziv, Y LeCun, M Bethge - ar** the online data buffering and organizing mechanism for continual test-time adaptation
Z Zhu, X Hong, Z Ma, W Zhuang, Y Ma, Y Dai… - … on Computer Vision, 2024 - Springer
Abstract Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source
model to continually changing unsupervised target domains. In this paper, we systematically …

AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation

T Lee, S Chottananurak, T Gong… - Proceedings of the …, 2024 - openaccess.thecvf.com
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 …

STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay

Y Yu, L Sheng, R He, J Liang - European Conference on Computer Vision, 2024 - Springer
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 …

Stationary latent weight inference for unreliable observations from online test-time adaptation

JH Lee, JH Chang - Forty-first International Conference on Machine …, 2024 - openreview.net
In the rapidly evolving field of online test-time adaptation (OTTA), effectively managing
distribution shifts is a pivotal concern. State-of-the-art OTTA methodologies often face …

Beyond model adaptation at test time: A survey

Z **ao, CGM Snoek - arxiv preprint arxiv:2411.03687, 2024 - arxiv.org
Machine learning algorithms have achieved remarkable success across various disciplines,
use cases and applications, under the prevailing assumption that training and test samples …

Santa: Source anchoring network and target alignment for continual test time adaptation

G Chakrabarty, M Sreenivas… - Transactions on Machine …, 2023 - openreview.net
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 …