Go to NeurIPS 2025 Conference homepageReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
Keywords: Test-Time Adaptation, Domain Shift, Catastrophic Forgetting, Recurring Domains
TL;DR: ReservoirTTA extends test-time adaptation to multiple model adaptation with a fully test-time reservoir of domain-specialist models for robust prolonged/long-horizon adaptation.
Abstract: 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.
Primary Area: General machine learning (supervised, unsupervised, online, active, etc.)
Submission Number: 16321
Loading