Test-Time Training with Masked Autoencoders
Yossi Gandelsman · Yu Sun · Xinlei Chen · Alexei Efros
2022 Poster
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.
Video
Chat is not available.
Successful Page Load