让模型在测试时持续学习，自动适应新领域。
TestDG: Test-time Domain Generalization for Continual Test-time Adaptation
- 在线学习跨领域不变特征，兼顾当前与过往领域
- 在4个公开基准上达到最先进性能
- 适合需要长期适应新数据的部署场景
本文研究持续测试时自适应（CTTA），即在测试过程中持续适应不断变化的未见领域，同时保留先前学习的知识。现有方法多只关注当前测试域的适应，忽视了未来可能遇到任意新领域的泛化能力。为此，我们提出一种新的在线测试时领域泛化框架TestDG，旨在测试过程中实时学习对当前及历史测试域均不变的特征，提升对未来未知领域的泛化潜力。TestDG引入新型模型架构、测试时自适应策略，以及用于高效管理历史信息的数据结构和优化算法。实验表明，TestDG在四个公开的CTTA基准上达到当前最优表现，并展现出更强的对未见测试域的泛化能力。
原文摘要 · Abstract (English)
This paper studies continual test-time adaptation (CTTA), the task of adapting a model to constantly changing unseen domains in testing while preserving previously learned knowledge. Existing CTTA methods mostly focus on adaptation to the current test domain only, overlooking generalization to arbitrary test domains a model may face in the future. To tackle this limitation, we present a novel online test-time domain generalization framework for CTTA, dubbed TestDG. TestDG aims to learn features invariant to both current and previous test domains on the fly during testing, improving the potential for effective generalization to future domains. To this end, we propose a new model architecture and a test-time adaptation strategy dedicated to learning domain-invariant features, along with a new data structure and optimization algorithm for effectively managing information from previous test domains. TestDG achieved state of the art on four public CTTA benchmarks. Moreover, it showed superior generalization to unseen test domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。