Score: 1

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

Published: November 23, 2025 | arXiv ID: 2511.18468v1

By: Md Akil Raihan Iftee , Mir Sazzat Hossain , Rakibul Hasan Rajib and more

Potential Business Impact:

Keeps AI smart on new and old tasks.

Business Areas:
EdTech Education, Software

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.

Page Count
38 pages

Category
Computer Science:
Machine Learning (CS)