Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:9229-9248, 2020.
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.