解决标签噪声下的异常检测难题，提升模型在真实场景的可靠性。
Tackling the Noisy Elephant in the Room: Label Noise-robust Out-of-Distribution Detection via Loss Correction and Low-rank Decomposition
- 结合损失修正与低秩分解，从源头缓解标签噪声影响
- 在严重标签噪声下，性能显著超越现有最优方法
- 适合安全关键场景中需高鲁棒性的异常检测任务
鲁棒的分布外（OOD）检测是现代人工智能系统不可或缺的组成部分，尤其在安全关键应用中，模型必须识别训练阶段未见的陌生类别输入。尽管机器学习领域已广泛研究了OOD检测，包括后处理和基于训练的方法，但在标签噪声环境下的有效性仍缺乏深入探索。近期研究表明，标签噪声会显著降低OOD检测性能，但针对性解决方案尚不完善。本文证明，直接将现有的标签噪声鲁棒方法与OOD检测策略结合，无法有效应对该挑战。为此，我们提出一种融合噪声标签学习中的损失修正技术与信号处理中的低秩稀疏分解方法的鲁棒OOD检测框架。在合成及真实数据集上的大量实验表明，该方法在严重标签噪声条件下显著优于现有最先进的OOD检测技术。
原文摘要 · Abstract (English)
Robust out-of-distribution (OOD) detection is an indispensable component of modern artificial intelligence (AI) systems, especially in safety-critical applications where models must identify inputs from unfamiliar classes not seen during training. While OOD detection has been extensively studied in the machine learning literature--with both post hoc and training-based approaches--its effectiveness under noisy training labels remains underexplored. Recent studies suggest that label noise can significantly degrade OOD performance, yet principled solutions to this issue are lacking. In this work, we demonstrate that directly combining existing label noise-robust methods with OOD detection strategies is insufficient to address this critical challenge. To overcome this, we propose a robust OOD detection framework that integrates loss correction techniques from the noisy label learning literature with low-rank and sparse decomposition methods from signal processing. Extensive experiments on both synthetic and real-world datasets demonstrate that our method significantly outperforms the state-of-the-art OOD detection techniques, particularly under severe noisy label settings.
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。