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.
Cite
Text
Sun et al. "Test-Time Training with Self-Supervision for Generalization Under Distribution Shifts." International Conference on Machine Learning, 2020.Markdown
[Sun et al. "Test-Time Training with Self-Supervision for Generalization Under Distribution Shifts." International Conference on Machine Learning, 2020.](https://mlanthology.org/icml/2020/sun2020icml-testtime/)BibTeX
@inproceedings{sun2020icml-testtime,
title = {{Test-Time Training with Self-Supervision for Generalization Under Distribution Shifts}},
author = {Sun, Yu and Wang, Xiaolong and Liu, Zhuang and Miller, John and Efros, Alexei and Hardt, Moritz},
booktitle = {International Conference on Machine Learning},
year = {2020},
pages = {9229-9248},
volume = {119},
url = {https://mlanthology.org/icml/2020/sun2020icml-testtime/}
}