Test Time Adaptation with Auxiliary Tasks

Motasem Alfarra, Alvaro Correia, Bernard Ghanem, Christos Louizos

Primary Area: transfer learning, meta learning, and lifelong learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Test Time Adaptation, Auxiliary Tasks

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose a distillation-based auxiliary task to accelerate adaptation to distribution shifts at test time.

Abstract: This work work tackles a key challenge in Test Time Adaptation~(TTA): adapting on limited data. This challenge arises naturally from two scenarios. (i) Current TTA methods are limited by the bandwidth with which the stream reveals data, since conducting several adaptation steps on each revealed batch from the stream will lead to overfitting. (ii) In many realistic scenarios, the stream reveals insufficient data for the model to fully adapt to a given distribution shift. We tackle the first scenario problem with auxiliary tasks where we leverage unlabeled data from the training distribution. In particular, we propose distilling the predictions of an originally pretrained model on clean data during adaptation. We found that our proposed auxiliary task significantly accelerates the adaptation to distribution shifts. We report a performance improvement over the state of the art by 1.5% and 6% on average across all corruptions on ImageNet-C under episodic and continual evaluation, respectively. To combat the second scenario of limited data, we analyze the effectiveness of combining federated adaptation with our proposed auxiliary task across different models even when different clients observe different distribution shifts. We find that not only federated averaging enhances adaptation, but combining it with our auxiliary task provides a notable 6% performance improvement over previous TTA methods.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 3415