Papers › TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision

TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision

18 May 2022arXiv:2205.08731archive 2025-07-28

Alexander Bartler, Florian Bender, Felix Wiewel, Bin Yang

Nowadays, deep neural networks outperform humans in many tasks. However, if the input distribution drifts away from the one used in training, their performance drops significantly. Recently published research has shown that adapting the model parameters to the test sample can mitigate this performance degradation. In this paper, we therefore propose a novel modification of the self-supervised training algorithm SwAV that adds the ability to adapt to single test samples. Using the provided prototypes of SwAV and our derived test-time loss, we align the representation of unseen test samples with the self-supervised learned prototypes. We show the success of our method on the common benchmark dataset CIFAR10-C.

PaperPDFCode

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

Code

alexanderbartler/ttaps officialmentioned in paperpytorch 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

ALIGNLARSSwAV

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