计算机视觉中的持续测试时间适应:方法、基准和未来方向
Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions
浏览论文内容
中文总结 AI 辅助
本文针对计算机视觉中训练与测试数据分布不同的问题,定义CTTA问题,分析持续域转移模式,提出分层分类法将现有方法分为三类,回顾代表性方法并展示实验结果,讨论局限性与新兴方向,为持续测试时间适应研究提供路线图。
中文摘要 AI 辅助
当训练和测试数据具有相同分布时,深度神经网络表现出色,但在实际部署中该假设常不成立,数据会持续发生分布变化。持续测试时间适应(CTTA)通过即时将预训练模型适应非平稳目标分布来应对这一挑战,且无需访问源数据或有标签目标,同时减轻两种关键失败模式:源知识的灾难性遗忘和长时间噪声伪标签导致的错误积累。在这项全面综述中,我们正式定义CTTA问题,分析不同评估协议的各种持续域转移模式,提出一种分层分类法,将现有方法分为三类:基于优化的策略(熵最小化、伪标签、参数恢复)、参数高效方法(归一化层适应、自适应参数选择)和基于架构的方法(师生框架、适配器、视觉提示、掩码建模)。我们系统地回顾了每类中的代表性方法,并展示了跨标准评估设置的比较基准和实验结果。最后,我们讨论了当前方法的局限性并突出了新兴研究方向,包括基础模型和黑盒系统的适应,为稳健的持续测试时间适应的未来研究提供了路线图。我们鼓励访问我们的资源库[此https URL](此https URL)
英文摘要
Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts. Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly, without access to source data or labeled targets, while mitigating two critical failure modes: catastrophic forgetting of source knowledge and error accumulation from noisy pseudo-labels over extended time horizons. In this comprehensive survey, we formally define the CTTA problem, analyze the diverse continual domain shift patterns that characterize different evaluation protocols, and propose a hierarchical taxonomy that categorizes existing methods into three families: optimization-based strategies (entropy minimization, pseudo-labeling, parameter restoration), parameter-efficient methods (normalization layer adaptation, adaptive parameter selection), and architecture-based approaches (teacher-student frameworks, adapters, visual prompting, masked modeling). We systematically review representative methods within each category and present comparative benchmarks and experimental results across standard evaluation settings. Finally, we discuss the limitations of current approaches and highlight emerging research directions, including the adaptation of foundation models and black-box systems, thereby providing a roadmap for future research in robust continual test-time adaptation.
发表机构
- The University of Texas at Dallas(德克萨斯大学达拉斯分校)
- LIVIA ETS Montreal, ILLS International Laboratory on Learning Systems (ILLS)(蒙特利尔LIVIA ETS,学习系统国际实验室(ILLS))
- Tulane University(路易斯安那州立大学)
- Nanyang Technological University(南洋理工大学)
- Hanyang University(翰阳大学)
机构由 AI 辅助整理,请以论文原文为准。