通过子空间对齐进行回归的测试时自适应
Test-time Adaptation for Regression by Subspace Alignment
- NTT Corporation（NTT公司）
- Kyoto University（京都大学）
- Yokohama National University（横滨国立大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出显著子空间对齐（SSA）方法，通过检测显著子空间并加权维度，解决回归任务中测试时自适应因特征分布稀疏而无效的问题，实验证明优于基线。
AI中文摘要：
本文研究了回归任务的测试时自适应（TTA），其中在源域预训练的回归模型被适应到未知的目标分布，且仅使用无标签的目标数据。尽管回归是机器学习中的基本任务之一，但大多数现有的TTA方法都是针对分类设计的，它们假设模型输出类别预测，而回归模型通常只输出单个标量值。为了实现回归的TTA，我们采用特征对齐方法，该方法对齐源域和目标域之间的特征分布以缓解域差距。然而，我们发现现有TTA方法中用于分类的朴素特征对齐在回归中效果不佳甚至更差，因为特征分布在一个小子空间中，且许多原始特征维度对输出几乎没有意义。为了在回归的TTA中实现有效的特征对齐，我们提出了显著子空间对齐（SSA）。SSA由两个组件组成：子空间检测和维度加权。子空间检测找到对输出具有代表性和显著性的特征子空间。然后，在TTA期间在该子空间内进行特征对齐。同时，维度加权提高了特征子空间中那些对输出具有更大显著性的维度的重要性。我们通过实验证明，SSA在真实世界数据集上优于各种基线方法。
英文摘要：
This paper investigates test-time adaptation (TTA) for regression, where a regression model pre-trained in a source domain is adapted to an unknown target distribution with unlabeled target data. Although regression is one of the fundamental tasks in machine learning, most of the existing TTA methods have classification-specific designs, which assume that models output class-categorical predictions, whereas regression models typically output only single scalar values. To enable TTA for regression, we adopt a feature alignment approach, which aligns the feature distributions between the source and target domains to mitigate the domain gap. However, we found that naive feature alignment employed in existing TTA methods for classification is ineffective or even worse for regression because the features are distributed in a small subspace and many of the raw feature dimensions have little significance to the output. For an effective feature alignment in TTA for regression, we propose Significant-subspace Alignment (SSA). SSA consists of two components: subspace detection and dimension weighting. Subspace detection finds the feature subspace that is representative and significant to the output. Then, the feature alignment is performed in the subspace during TTA. Meanwhile, dimension weighting raises the importance of the dimensions of the feature subspace that have greater significance to the output. We experimentally show that SSA outperforms various baselines on real-world datasets.
