Papers › Test-Time Training with Masked Autoencoders

Test-Time Training with Masked Autoencoders

15 Sep 2022arXiv:2209.07522archive 2025-07-28

Yossi Gandelsman, Yu Sun, Xinlei Chen, Alexei A. Efros

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yossigandelsman/test_time_training_mae officialmentioned on GitHubpytorch report
Rima-ag/TTT-MAE mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Test

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections