BECoTTA：用于持续测试时适应的输入依赖型专家在线混合
BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
AI总结：
本文提出BECoTTA框架，通过包含领域自适应路由和领域-专家协同损失的领域低秩专家混合（MoDE）机制，在持续测试时适应中实现高效适应与知识保留的平衡，同时显著减少可训练参数。
摘要：
持续测试时适应（CTTA）需要在保留已学知识的同时，高效适应连续的未见领域。然而，尽管CTTA取得了进展，但部署具有更优的遗忘-适应权衡和效率的模型仍具挑战。此外，当前的CTTA场景仅假设不相交的情况，尽管现实世界的领域是无缝变化的。为应对这些挑战，本文提出了BECoTTA，一个用于CTTA的输入依赖且高效的模块化框架。我们提出了领域低秩专家混合（MoDE），包含两个核心组件：（i）领域自适应路由，借助多个领域路由器帮助选择性地捕获领域自适应知识；以及（ii）领域-专家协同损失，用于最大化每个领域与专家之间的依赖性。我们验证了我们的方法在多个CTTA场景（包括不相交和渐进的领域偏移）中均优于其他方法，同时仅需减少约98%的可训练参数。我们还提供了方法分析，包括专家构建、领域自适应专家的作用及可视化。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
