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, forgetting-adaptation trade-offs and efficiency are still unexplored. Moreover, current CTTA scenarios assume only the disjoint situation, even though real-world domains are seamlessly changed. To tackle these challenges, this paper proposes BECoTTA, an input-dependent yet efficient framework for CTTA. We propose Mixture-of-Domain Low-rank Experts (MoDE) that contains two core components: (i) Domain-Adaptive Routing, which aids in selectively capturing 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 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.

翻译：持续测试时自适应（CTTA）要求模型在高效适应持续出现的未知域的同时，保留先前学习到的知识。然而，尽管CTTA已取得进展，但遗忘-适应权衡与效率问题仍未得到充分探索。此外，当前CTTA场景仅假设域不连续变化的情形，而现实世界的域往往是平滑渐变的。为解决这些挑战，本文提出BECoTTA——一种输入依赖且高效的CTTA框架。我们提出了混合域低秩专家（MoDE）模块，其包含两个核心组件：（i）域自适应路由，通过多个域路由器选择性捕获域自适应知识；（ii）域-专家协同损失，最大化每个域与对应专家之间的依赖性。实验表明，我们的方法在包括不连续与渐变域偏移在内的多种CTTA场景中均取得更优性能，且可训练参数减少约98%。我们还提供了方法分析，包括专家构建机制、域自适应专家效果及可视化结果。