“Test-Time Training With Masked Autoencoders”, Yossi Gandelsman, Yu Sun, Xinlei Chen, Alexei A. Efros2022-09-15 (, ; similar)⁠:

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.