@inproceedings{66f37e01866f4d20998104a5129eeb85,
title = "Test-time training with self-supervision for generalization under distribution shifts",
abstract = "In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised learning problem, on which we update the model parameters before making a prediction. This also extends naturally to data in an online stream. Our simple approach leads to improvements on diverse image classification benchmarks aimed at evaluating robustness to distribution shifts.",
author = "Yu Sun and Xiaolong Wang and Zhuang Liu and John Miller and Efros, \{Alexei A.\} and Moritz Hardt",
note = "Publisher Copyright: {\textcopyright} 2020 37th International Conference on Machine Learning, ICML 2020. All rights reserved.; 37th International Conference on Machine Learning, ICML 2020 ; Conference date: 13-07-2020 Through 18-07-2020",
year = "2020",
language = "English (US)",
series = "37th International Conference on Machine Learning, ICML 2020",
publisher = "International Machine Learning Society (IMLS)",
pages = "9166--9185",
editor = "Hal Daume and Aarti Singh",
booktitle = "37th International Conference on Machine Learning, ICML 2020",
}