提出无源测试时回归校准方法，提升模型在分布偏移下的稳定性。
Predictive Spectral Calibration for Source-Free Test-Time Regression
- 通过块谱匹配实现目标特征与源预测空间对齐
- 在严重分布偏移下性能超越强基线方法
- 无需源数据，适配预训练回归模型
图像回归的测试时自适应（TTA）研究远少于分类任务。现有分类方法依赖分类特定目标和决策边界，难以直接迁移至连续回归任务。近期工作通过子空间对齐重新探索回归TTA，表明简单源引导对齐既实用又有效。本文提出预测谱校准（PSC），一种无源框架，将子空间对齐扩展至块谱匹配。PSC不依赖固定支持子空间，而是联合对齐目标特征在源预测支持空间中的表示，并校准正交补空间中的残差谱松弛。该方法实现简单、模型无关，兼容现成预训练回归器。在多个图像回归基准上实验表明，相较于强基线方法，性能持续提升，尤其在严重分布偏移下表现显著。
原文摘要 · Abstract (English)
Test-time adaptation (TTA) for image regression has received far less attention than its classification counterpart. Methods designed for classification often depend on classification-specific objectives and decision boundaries, making them difficult to transfer directly to continuous regression targets. Recent progress revisits regression TTA through subspace alignment, showing that simple source-guided alignment can be both practical and effective. Building on this line of work, we propose Predictive Spectral Calibration (PSC), a source-free framework that extends subspace alignment to block spectral matching. Instead of relying on a fixed support subspace alone, PSC jointly aligns target features within the source predictive support and calibrates residual spectral slack in the orthogonal complement. PSC remains simple to implement, model-agnostic, and compatible with off-the-shelf pretrained regressors. Experiments on multiple image regression benchmarks show consistent improvements over strong baselines, with particularly clear gains under severe distribution shifts.
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。