DPCore：用于持续测试时自适应的动态提示核心集
DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation
AI总结：
DPCore针对持续测试时自适应中域动态变化问题，提出结合视觉提示自适应、提示核心集和动态更新机制的方法，在四个基准上以更少参数和计算时间实现最优性能。
摘要：
持续测试时自适应（CTTA）旨在使源预训练模型适应不断变化的、未见过的目标域。现有的CTTA方法假设域变化是结构化的且持续时间均匀，但现实环境往往表现出动态模式，其中域以不同的频率和持续时间反复出现。当前方法在不同域上自适应相同的参数，在这种动态条件下表现不佳——它们在域暴露时间较短时面临收敛问题，存在遗忘先前所学知识的风险，或将其错误地应用于不相关的域。为了解决这一问题，我们提出了DPCore，一种旨在跨多样化域变化模式实现鲁棒性能同时确保计算效率的方法。DPCore集成了三个关键组件：用于高效域对齐的视觉提示自适应（Visual Prompt Adaptation）、用于知识保留的提示核心集（Prompt Coreset），以及一种动态更新机制，该机制智能地调整相似域的现有提示，同时为显著不同的域创建新提示。在四个基准上的大量实验表明，DPCore始终优于各种CTTA方法，在结构化和动态设置下均达到了最先进的性能，同时与先前方法相比，可训练参数减少了99%，计算时间减少了64%。
英文摘要：
Continual Test-Time Adaptation (CTTA) seeks to adapt source pre-trained models to continually changing, unseen target domains. While existing CTTA methods assume structured domain changes with uniform durations, real-world environments often exhibit dynamic patterns where domains recur with varying frequencies and durations. Current approaches, which adapt the same parameters across different domains, struggle in such dynamic conditions-they face convergence issues with brief domain exposures, risk forgetting previously learned knowledge, or misapplying it to irrelevant domains. To remedy this, we propose DPCore, a method designed for robust performance across diverse domain change patterns while ensuring computational efficiency. DPCore integrates three key components: Visual Prompt Adaptation for efficient domain alignment, a Prompt Coreset for knowledge preservation, and a Dynamic Update mechanism that intelligently adjusts existing prompts for similar domains while creating new ones for substantially different domains. Extensive experiments on four benchmarks demonstrate that DPCore consistently outperforms various CTTA methods, achieving state-of-the-art performance in both structured and dynamic settings while reducing trainable parameters by 99% and computation time by 64% compared to previous approaches.
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。
