Mining In-distribution Attributes in Outliers for Out-of-distribution Detection
It addresses the problem of reliable OOD detection for deploying machine learning systems, but appears incremental as it builds on prior work using auxiliary outliers.
The paper tackles out-of-distribution (OOD) detection by identifying that OOD data often contains significant in-distribution attributes, which should be rationally handled rather than suppressed, and proposes a multi-view-based framework (MVOL) that shows superiority in experiments.
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.