Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation

TL;DR

This paper introduces DOCO, a novel framework for open-set continual test-time adaptation that improves domain adaptation and out-of-distribution detection under dynamic, real-world conditions.

Contribution

The paper proposes a lightweight, closed-loop method that separates ID and OOD samples, learns domain compensation prompts, and enhances OCTTA performance.

Findings

DOCO outperforms prior methods on multiple benchmarks.

It effectively separates ID and OOD samples during adaptation.

The framework maintains semantic integrity while adapting to domain shifts.

Abstract

Test-Time Adaptation (TTA) aims to mitigate distributional shifts between training and test domains during inference time. However, existing TTA methods fall short in the realistic scenario where models face both continually changing domains and the simultaneous emergence of unknown semantic classes, a challenging setting we term Open-set Continual Test-Time Adaptation (OCTTA). The coupling of domain and semantic shifts often collapses the feature space, severely degrading both classification and out-of-distribution detection. To tackle this, we propose DOmain COmpensation (DOCO), a lightweight and effective framework that robustly performs domain adaptation and OOD detection in a synergistic, closed loop. DOCO first performs dynamic, adaptation-conditioned sample splitting to separate likely ID from OOD samples. Then, using only the ID samples, it learns a domain compensation prompt by aligning feature statistics with the source domain, guided by a structural preservation regularizer that prevents semantic distortion. This learned prompt is then propagated to the OOD samples within the same batch, effectively isolating their semantic novelty for more reliable detection. Extensive experiments on multiple challenging benchmarks demonstrate that DOCO outperforms prior CTTA and OSTTA methods, establishing a new state-of-the-art for the demanding OCTTA setting.