发现异常数据中隐藏的正常属性，提升模型识别异常能力。
Mining In-distribution Attributes in Outliers for Out-of-distribution Detection
- 利用多视角框架挖掘异常样本中的正常特征
- 在多个数据集上实现优于现有方法的检测效果
- 适合需要高可靠性部署的工业级模型场景
分布外（OOD）检测对真实场景下可靠机器学习系统部署至关重要。近期工作虽通过训练时引入辅助异常数据展现潜力，但很少关注正常与异常数据间的内在关联。本文发现：异常数据通常显著包含正常属性，这些属性应被纳入训练过程，而非像以往方法那样盲目压制。基于此洞察，提出结构化多视角分布外检测学习（MVOL）框架，合理处理异常样本中的正常属性。提供了关于MVOL有效性的理论分析。大量实验表明，该框架显著优于现有方法，能有效利用辅助异常数据，甚至可处理含噪声正常数据的野数据集。代码已开源：https://github.com/UESTC-nnLab/MVOL。
原文摘要 · Abstract (English)
Out-of-distribution (OOD) detection is indispensable for deploying reliable machine learning systems in real-world scenarios. Recent works, using auxiliary outliers in training, have shown good potential. However, they seldom concern the intrinsic correlations between in-distribution (ID) and OOD data. In this work, we discover an obvious correlation that OOD data usually possesses significant ID attributes. These attributes should be factored into the training process, rather than blindly suppressed as in previous approaches. Based on this insight, we propose a structured multi-view-based out-of-distribution detection learning (MVOL) framework, which facilitates rational handling of the intrinsic in-distribution attributes in outliers. We provide theoretical insights on the effectiveness of MVOL for OOD detection. Extensive experiments demonstrate the superiority of our framework to others. MVOL effectively utilizes both auxiliary OOD datasets and even wild datasets with noisy in-distribution data. Code is available at https://github.com/UESTC-nnLab/MVOL.
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。