挖掘离群样本中的分布内属性用于分布外检测
Mining In-distribution Attributes in Outliers for Out-of-distribution Detection
AI总结：
本文发现OOD数据常含显著ID属性，提出结构化多视图MVOL框架合理利用而非抑制这些属性，理论验证有效性，实验证明优于现有方法。
摘要：
分布外（OOD）检测对于在现实场景中部署可靠的机器学习系统不可或缺。近期利用辅助离群样本进行训练的工作展现出良好潜力，然而它们很少关注分布内（ID）与OOD数据之间的内在关联。本工作中，我们发现了明显的关联：OOD数据通常具有显著的ID属性。这些属性应被纳入训练过程，而非像先前方法那样被盲目抑制。基于此见解，我们提出结构化多视图分布外检测学习（MVOL）框架，该框架合理处理离群样本中的内在分布内属性。我们为MVOL在OOD检测中的有效性提供了理论见解。大量实验证明了我们框架相对于其他方法的优越性。MVOL有效利用辅助OOD数据集，甚至包含噪声分布内数据的野生数据集。代码可在https://github.com/UESTC-nnLab/MVOL获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
