“Test-Time Training With Self-Supervision for Generalization under Distribution Shifts”, Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A. Efros, Moritz Hardt2019-09-29 (dynamic evaluation (NN))⁠:

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.