Test-Time Training with Masked Autoencoders

Understand

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.