黄金子空间：在持续测试时适应中效率与泛化的平衡
The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation
AI总结：
本文提出GOLD方法，通过轻量级适配器将特征投影到黄金子空间，并动态更新子空间以提升效率和稳定性，实验证明其在分类和分割任务中表现优异。
摘要：
持续测试时适应（CTTA）旨在使模型能够在线适应分布偏移的无标签数据流，而无需访问源数据。现有CTTA方法面临效率与泛化的权衡：更新更多参数可提高适应性但会严重降低在线推理效率。我们证明在单步适应设置中存在黄金子空间，并显示其与预训练分类器的行空间一致。为实现该子空间的在线维护，我们引入样本级平均梯度外积（AGOP）作为估计分类器权重的高效代理。基于这些见解，我们提出引导在线低秩方向适应（GOLD），通过轻量级适配器将特征投影到黄金子空间，并在子空间动态更新过程中学习紧凑的缩放向量。在分类和分割基准测试中，包括自动驾驶场景，GOLD在效率、稳定性和整体性能上均优于现有方法。我们的代码可在https://github.com/AIGNLAI/GOLD获取。
英文摘要：
Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data. Existing CTTA methods face an efficiency-generalization trade-off: updating more parameters improves adaptation but severely reduces online inference efficiency. An ideal solution is to achieve comparable adaptation with minimal feature updates; we call this minimal subspace the golden subspace. We prove its existence in a single-step adaptation setting and show that it coincides with the row space of the pretrained classifier. To enable online maintenance of this subspace, we introduce the sample-wise Average Gradient Outer Product (AGOP) as an efficient proxy for estimating the classifier weights without retraining. Building on these insights, we propose Guided Online Low-rank Directional adaptation (GOLD), which uses a lightweight adapter to project features onto the golden subspace and learns a compact scaling vector while the subspace is dynamically updated via AGOP. Extensive experiments on classification and segmentation benchmarks, including autonomous-driving scenarios, demonstrate that GOLD attains superior efficiency, stability, and overall performance. Our code is available at https://github.com/AIGNLAI/GOLD.
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。
