回归源头：通过域补偿实现开放集持续测试时自适应
Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation
把「域补偿提示词」作为可复用手段：仅用疑似 ID 样本对齐源域特征统计（一阶/二阶矩）来学习提示词，再传播到同批次 OOD 样本上，从而在持续变化的域中同时稳住分类与 OOD 检测；做测试时自适应或开放集部署时可直接借用这套样本拆分+提示词传播的闭环。
原文依据 it learns a domain compensation prompt by aligning feature statistics with the source domain
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论测试时自适应（TTA）旨在推理阶段缓解训练域与测试域之间的分布偏移。然而，现有 TTA 方法在模型同时面临不断变化的域以及未知语义类别同时涌现这一现实场景时表现不足——我们将这一具有挑战性的设定称为开放集持续测试时自适应（OCTTA）。域偏移与语义偏移的耦合往往导致特征空间坍塌，严重损害分类性能与分布外检测能力。为解决这一问题，我们提出域补偿（DOCO），一个轻量且有效的框架，以协同的闭环方式稳健地执行域自适应与 OOD 检测。DOCO 首先执行动态的、以自适应状态为条件的样本拆分，将可能的 ID 样本与 OOD 样本分离。随后，仅使用 ID 样本，通过将特征统计量与源域对齐来学习域补偿提示词，并由一个防止语义扭曲的结构保持正则项加以引导。该学习到的提示词随后被传播到同一批次内的 OOD 样本上，从而有效分离其语义新颖性，实现更可靠的检测。在多个具有挑战性的基准上的大量实验表明，DOCO 优于先前的 CTTA 与 OSTTA 方法，为要求严苛的 OCTTA 设定建立了新的最优性能。
英文原文摘要 1382 字符
Test-Time Adaptation (TTA) aims to mitigate distributional shifts between training and test domains during inference time. However, existing TTA methods fall short in the realistic scenario where models face both continually changing domains and the simultaneous emergence of unknown semantic classes --- a challenging setting we term Open-set Continual Test-Time Adaptation (OCTTA). The coupling of domain and semantic shifts often collapses the feature space, severely degrading both classification and out-of-distribution detection. To tackle this, we propose DOmain COmpensation (DOCO), a lightweight and effective framework that robustly performs domain adaptation and OOD detection in a synergistic, closed loop. DOCO first performs dynamic, adaptation-conditioned sample splitting to separate likely ID from OOD samples. Then, using only the ID samples, it learns a domain compensation prompt by aligning feature statistics with the source domain, guided by a structural preservation regularizer that prevents semantic distortion. This learned prompt is then propagated to the OOD samples within the same batch, effectively isolating their semantic novelty for more reliable detection. Extensive experiments on multiple challenging benchmarks demonstrate that DOCO outperforms prior CTTA and OSTTA methods, establishing a new state-of-the-art for the demanding OCTTA setting.