用局部几何结构提升噪声下正负样本学习的鲁棒性
From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift
- 基于视觉特征局部流形结构，逐步识别分布偏移数据
- 在多种偏移场景下性能媲美全监督方法，准确率超90%
- 适合无标注偏移数据的现实场景，对噪声不敏感
检测协变量偏移对构建可靠视觉系统至关重要。现有方法多聚焦于提升对偏移的鲁棒性，但显式检测偏移仍研究不足。多数方法依赖全监督训练，需原分布与偏移分布的标注样本，实际难以实现。本文表明，在弱监督下可通过正样本-未标注样本（PU）学习有效解决偏移检测问题。然而，当分布内与偏移数据重叠度高时，经典PU方法易受噪声干扰且不稳定。为此，我们提出谱式邻域标注（SPUNA），一种利用视觉特征局部流形结构的几何感知框架，可逐步发现偏移数据。大量实验表明，SPUNA在PU设置中达到领先性能，显著接近全监督方法表现。此外，该方法在不同偏移类型间具有良好迁移能力，展现出强泛化性。代码已开源。
原文摘要 · Abstract (English)
Detecting covariate shift is critical for building reliable vision systems. While most prior work focuses on improving robustness to shift, explicitly detecting covariate shift remains underexplored. Existing approaches typically rely on fully supervised training, requiring labeled examples from both original and shifted distributions, which is often impractical. In this paper, we show that covariate shift detection can be effectively addressed with weaker supervision using Positive Unlabeled (PU) learning. However, under covariate shift, in distribution and shifted data overlap significantly, making classical PU methods unstable and sensitive to noise. To overcome this challenge, we introduce Spectral PU Neighborhood Annotation (SPUNA), a geometry aware framework that progressively discovers shifted data by leveraging the local manifold structure of visual features. Extensive experiments show that SPUNA achieves state of the art performance in PU settings and remarkably matches the performances of fully supervised methods. Moreover, our approach transfers robustly across different types of shifts, demonstrating strong generalization capabilities. Code is available at https://github.com/fira7s/S-PUNA
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。