新方法通过优化类别原型，有效抑制虚假相关性，提升模型对分布外数据的检测可靠性。
Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
- 基于原型改进，后处理方式消除虚假特征带来的偏差。
- 在多个挑战性数据集上平均提升AUROC 4.8%，FPR@95降低9.4%。
- 无需额外数据或调参，适配多种模型和检测场景。
分布外（OOD）检测对保障机器学习模型在真实场景中的可靠性和安全性至关重要，因为实际应用中模型常遇到训练时未见的数据分布。尽管已有进展，现有方法仍易受虚假相关性干扰，导致性能下降。为此，我们提出SPROD——一种新型原型驱动的OOD检测方法，明确应对未知虚假相关性的挑战。该后处理方法通过优化类别原型，消除虚假特征带来的偏差，无需额外数据或超参数调优，适用于多种骨干网络和检测设置。我们在包含CelebA、Waterbirds、UrbanCars、Spurious Imagenet及新提出的Animals MetaCoCo在内的多个挑战性数据集上进行了全面评测，结果表明，SPROD在平均性能上较次优方法提升AUROC 4.8%，FPR@95降低9.4%。
原文摘要 · Abstract (English)
Out-of-distribution (OOD) detection is crucial for ensuring the reliability and safety of machine learning models in real-world applications, where they frequently face data distributions unseen during training. Despite progress, existing methods are often vulnerable to spurious correlations that mislead models and compromise robustness. To address this, we propose SPROD, a novel prototype-based OOD detection approach that explicitly addresses the challenge posed by unknown spurious correlations. Our post-hoc method refines class prototypes to mitigate bias from spurious features without additional data or hyperparameter tuning, and is broadly applicable across diverse backbones and OOD detection settings. We conduct a comprehensive spurious correlation OOD detection benchmarking, comparing our method against existing approaches and demonstrating its superior performance across challenging OOD datasets, such as CelebA, Waterbirds, UrbanCars, Spurious Imagenet, and the newly introduced Animals MetaCoCo. On average, SPROD improves AUROC by 4.8% and FPR@95 by 9.4% over the second best.
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。