Enregistré dans:
Détails bibliographiques
Auteurs principaux: Döbler, Mario, Marencke, Florian, Marsden, Robert A., Yang, Bin
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2401.00989
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914626931785728
author Döbler, Mario
Marencke, Florian
Marsden, Robert A.
Yang, Bin
author_facet Döbler, Mario
Marencke, Florian
Marsden, Robert A.
Yang, Bin
contents Since distribution shifts are likely to occur after a model's deployment and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model during test-time, leveraging the current test data. In real-world scenarios, test data streams are not always independent and identically distributed (i.i.d.). Instead, they are frequently temporally correlated, making them non-i.i.d. Many existing methods struggle to cope with this scenario. In response, we propose a diversity-aware and category-balanced buffer that can simulate an i.i.d. data stream, even in non-i.i.d. scenarios. Combined with a diversity and entropy-weighted entropy loss, we show that a stable adaptation is possible on a wide range of corruptions and natural domain shifts, based on ImageNet. We achieve state-of-the-art results on most considered benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2401_00989
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diversity-aware Buffer for Coping with Temporally Correlated Data Streams in Online Test-time Adaptation
Döbler, Mario
Marencke, Florian
Marsden, Robert A.
Yang, Bin
Computer Vision and Pattern Recognition
Since distribution shifts are likely to occur after a model's deployment and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model during test-time, leveraging the current test data. In real-world scenarios, test data streams are not always independent and identically distributed (i.i.d.). Instead, they are frequently temporally correlated, making them non-i.i.d. Many existing methods struggle to cope with this scenario. In response, we propose a diversity-aware and category-balanced buffer that can simulate an i.i.d. data stream, even in non-i.i.d. scenarios. Combined with a diversity and entropy-weighted entropy loss, we show that a stable adaptation is possible on a wide range of corruptions and natural domain shifts, based on ImageNet. We achieve state-of-the-art results on most considered benchmarks.
title Diversity-aware Buffer for Coping with Temporally Correlated Data Streams in Online Test-time Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.00989