SloMo-Fast: Slow-Momentum and Fast-Adaptive Teachers for Source-Free Continual Test-Time Adaptation

TL;DR

SloMo-Fast introduces a dual-teacher framework for source-free continual test-time adaptation, effectively balancing long-term knowledge retention and rapid adaptation to evolving target domains, with superior performance demonstrated on Cyclic-TTA and other benchmarks.

Contribution

The paper proposes SloMo-Fast, a novel dual-teacher approach with cyclic test-time adaptation, addressing long-term forgetting and privacy constraints in continual domain adaptation.

Findings

Outperforms state-of-the-art methods on Cyclic-TTA

Effectively balances knowledge retention and adaptation

Demonstrates robustness across multiple CTTA settings

Abstract

Continual Test-Time Adaptation (CTTA) is crucial for deploying models in real-world applications with unseen, evolving target domains. Existing CTTA methods, however, often rely on source data or prototypes, limiting their applicability in privacy-sensitive and resource-constrained settings. Additionally, these methods suffer from long-term forgetting, which degrades performance on previously encountered domains as target domains shift. To address these challenges, we propose SloMo-Fast, a source-free, dual-teacher CTTA framework designed for enhanced adaptability and generalization. It includes two complementary teachers: the Slow-Teacher, which exhibits slow forgetting and retains long-term knowledge of previously encountered domains to ensure robust generalization, and the Fast-Teacher rapidly adapts to new domains while accumulating and integrating knowledge across them. This framework preserves knowledge of past domains and adapts efficiently to new ones. We also introduce Cyclic Test-Time Adaptation (Cyclic-TTA), a novel CTTA benchmark that simulates recurring domain shifts. Our extensive experiments demonstrate that SloMo-Fast consistently outperforms state-of-the-art methods across Cyclic-TTA, as well as ten other CTTA settings, highlighting its ability to both adapt and generalize across evolving and revisited domains.