提出黄金子空间，在线适应中兼顾高效与泛化。
The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation
- 发现最优更新子空间即预训练分类器的行空间。
- 用AGOP动态维护子空间，仅更新少量参数。
- 适合实时场景，尤其自动驾驶图像任务。
持续测试时自适应（CTTA）旨在模型在线处理无标签数据流时，于分布偏移下实现自适应，且无需访问源数据。现有方法在效率与泛化间存在权衡：更新更多参数可提升适应性但严重降低推理效率。理想方案是仅通过最小特征更新实现相当适应效果，我们称此为黄金子空间。本文证明其在单步适应设定下存在，并与预训练分类器的行空间一致。为在线维护该子空间，引入样本级平均梯度外积（AGOP），作为无需重训练即可估计分类器权重的高效代理。基于上述发现，提出导向式在线低秩方向自适应（GOLD），利用轻量适配器将特征投影至黄金子空间，同时学习紧凑缩放向量，且通过AGOP动态更新子空间。在分类与分割基准，包括自动驾驶场景的大量实验表明，GOLD在效率、稳定性及整体性能上均表现优异。代码已公开于 https://github.com/AIGNLAI/GOLD。
原文摘要 · Abstract (English)
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.
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。