BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
This addresses the challenge of efficient and adaptable deployment of models in real-world scenarios with seamless domain shifts, though it is incremental in improving existing CTTA methods.
The paper tackles the problem of continual test-time adaptation (CTTA) by proposing BECoTTA, a modular framework that uses input-dependent blending of experts to adapt to continuous unseen domains while reducing forgetting, achieving state-of-the-art performance with ~98% fewer trainable parameters.
Continual Test Time Adaptation (CTTA) is required to adapt efficiently to continuous unseen domains while retaining previously learned knowledge. However, despite the progress of CTTA, it is still challenging to deploy the model with improved forgetting-adaptation trade-offs and efficiency. In addition, current CTTA scenarios assume only the disjoint situation, even though real-world domains are seamlessly changed. To address these challenges, this paper proposes BECoTTA, an input-dependent and efficient modular framework for CTTA. We propose Mixture-of Domain Low-rank Experts (MoDE) that contains two core components: (i) Domain-Adaptive Routing, which helps to selectively capture the domain adaptive knowledge with multiple domain routers, and (ii) Domain-Expert Synergy Loss to maximize the dependency between each domain and expert. We validate that our method outperforms multiple CTTA scenarios, including disjoint and gradual domain shits, while only requiring ~98% fewer trainable parameters. We also provide analyses of our method, including the construction of experts, the effect of domain-adaptive experts, and visualizations.