ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vray, Guillaume, Tomar, Devavrat, Gao, Xufeng, Thiran, Jean-Philippe, Shelhamer, Evan, Bozorgtabar, Behzad
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912590969438208
author Vray, Guillaume
Tomar, Devavrat
Gao, Xufeng
Thiran, Jean-Philippe
Shelhamer, Evan
Bozorgtabar, Behzad
author_facet Vray, Guillaume
Tomar, Devavrat
Gao, Xufeng
Thiran, Jean-Philippe
Shelhamer, Evan
Bozorgtabar, Behzad
contents This paper introduces ReservoirTTA, a novel plug-in framework designed for prolonged test-time adaptation (TTA) in scenarios where the test domain continuously shifts over time, including cases where domains recur or evolve gradually. At its core, ReservoirTTA maintains a reservoir of domain-specialized models -- an adaptive test-time model ensemble -- that both detects new domains via online clustering over style features of incoming samples and routes each sample to the appropriate specialized model, and thereby enables domain-specific adaptation. This multi-model strategy overcomes key limitations of single model adaptation, such as catastrophic forgetting, inter-domain interference, and error accumulation, ensuring robust and stable performance on sustained non-stationary test distributions. Our theoretical analysis reveals key components that bound parameter variance and prevent model collapse, while our plug-in TTA module mitigates catastrophic forgetting of previously encountered domains. Extensive experiments on scene-level corruption benchmarks (ImageNet-C, CIFAR-10/100-C), object-level style shifts (DomainNet-126, PACS), and semantic segmentation (Cityscapes->ACDC) covering recurring and continuously evolving domain shifts -- show that ReservoirTTA substantially improves adaptation accuracy and maintains stable performance across prolonged, recurring shifts, outperforming state-of-the-art methods. Our code is publicly available at https://github.com/LTS5/ReservoirTTA.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14511
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
Vray, Guillaume
Tomar, Devavrat
Gao, Xufeng
Thiran, Jean-Philippe
Shelhamer, Evan
Bozorgtabar, Behzad
Computer Vision and Pattern Recognition
This paper introduces ReservoirTTA, a novel plug-in framework designed for prolonged test-time adaptation (TTA) in scenarios where the test domain continuously shifts over time, including cases where domains recur or evolve gradually. At its core, ReservoirTTA maintains a reservoir of domain-specialized models -- an adaptive test-time model ensemble -- that both detects new domains via online clustering over style features of incoming samples and routes each sample to the appropriate specialized model, and thereby enables domain-specific adaptation. This multi-model strategy overcomes key limitations of single model adaptation, such as catastrophic forgetting, inter-domain interference, and error accumulation, ensuring robust and stable performance on sustained non-stationary test distributions. Our theoretical analysis reveals key components that bound parameter variance and prevent model collapse, while our plug-in TTA module mitigates catastrophic forgetting of previously encountered domains. Extensive experiments on scene-level corruption benchmarks (ImageNet-C, CIFAR-10/100-C), object-level style shifts (DomainNet-126, PACS), and semantic segmentation (Cityscapes->ACDC) covering recurring and continuously evolving domain shifts -- show that ReservoirTTA substantially improves adaptation accuracy and maintains stable performance across prolonged, recurring shifts, outperforming state-of-the-art methods. Our code is publicly available at https://github.com/LTS5/ReservoirTTA.
title ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.14511