Test-Time Training with Masked Autoencoders

Part of Advances in Neural Information Processing Systems 35 (NeurIPS 2022) Main Conference Track

Bibtex Paper Supplemental

Authors

Yossi Gandelsman, Yu Sun, Xinlei Chen, Alexei Efros

Abstract

Test-time training adapts to a new test distribution on the fly by optimizing a model for each test input using self-supervision.In this paper, we use masked autoencoders for this one-sample learning problem.Empirically, our simple method improves generalization on many visual benchmarks for distribution shifts.Theoretically, we characterize this improvement in terms of the bias-variance trade-off.