EUVIMEDEUVIMED entdecken
Crossref

A Layer Selection Approach to Test Time Adaptation

Sabyasachi Sahoo, Mostafa ElAraby, Jonas Ngnawe, Yann Batiste Pequignot, Frédéric Precioso, Christian Gagné

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (19) · 20237-20245

DOI: 10.1609/aaai.v39i19.34229 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Sabyasachi Sahoo und 5 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When faced with challenging shifts, most methods collapse and perform worse than the original pretrained model. In this paper, we find that not all layers are equally receptive to the adaptation, and the layers with the most misaligned gradients often cause performance degradation. To address this, we propose GALA, a novel layer selection criterion to identify the most beneficial updates to perform during test time adaptation. This criterion can also filter out unreliable samples with noisy gradients. Its simplicity allows seamless integration with existing TTA loss functions, thereby preventing degradation and focusing adaptation on the most trainable layers. This approach also helps to regularize adaptation to preserve the pretrained features, which are crucial for handling unseen domains. Through extensive experiments, we demonstrate that the proposed layer selection framework improves the performance of existing TTA approaches across multiple datasets, domain shifts, model architectures, and TTA losses.

Zitieren

APA

Sahoo, S., ElAraby, M., Ngnawe, J., Pequignot, Y. B., Precioso, F., & Gagné, C. (2025). A Layer Selection Approach to Test Time Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(19), 20237-20245. https://doi.org/10.1609/aaai.v39i19.34229

Vancouver

Sahoo S, ElAraby M, Ngnawe J, Pequignot YB, Precioso F, Gagné C. A Layer Selection Approach to Test Time Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(19):20237-20245. doi:10.1609/aaai.v39i19.34229

BibTeX
@article{Sahoo2025,
  author = {Sahoo, Sabyasachi and ElAraby, Mostafa and Ngnawe, Jonas and Pequignot, Yann Batiste and Precioso, Frédéric and Gagné, Christian},
  title = {A Layer Selection Approach to Test Time Adaptation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {19},
  pages = {20237--20245},
  doi = {10.1609/aaai.v39i19.34229}
}
Kostenlos starten →