BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation

TL;DR

BECoTTA introduces an input-dependent, efficient modular framework for continual test-time adaptation that improves domain adaptation performance while significantly reducing trainable parameters.

Contribution

It proposes MoDE, a novel mixture-of-experts approach with domain-adaptive routing and synergy loss for better continual test-time adaptation.

Findings

Outperforms existing CTTA methods in disjoint and gradual domain shifts.

Requires approximately 98% fewer trainable parameters.

Provides detailed analyses and visualizations of the method's components.

Abstract

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.