NeurIPS 2022accept191 citations
Test-Time Training with Masked Autoencoders
Yossi Gandelsman, Yu Sun, Xinlei Chen, Alexei A 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.
Computer VisionTest-Time TrainingMasked Auto-Encoder
BibTeX
@inproceedings{
gandelsman2022testtime,
title={Test-Time Training with Masked Autoencoders},
author={Yossi Gandelsman and Yu Sun and Xinlei Chen and Alexei A Efros},
booktitle={Advances in Neural Information Processing Systems},
editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
year={2022},
url={https://openreview.net/forum?id=SHMi1b7sjXk}
}