Hyperbolic Metric Learning for Visual Outlier Detection
This work addresses OOD detection for safety-critical applications by leveraging hyperbolic geometry to better capture hierarchical structures, offering incremental improvements over existing methods.
The paper tackles the problem of Out-Of-Distribution (OOD) detection in visual data by proposing a hyperbolic metric learning framework, which improves FPR95 from 22% to 15% on CIFAR-10 and from 49% to 28% on CIFAR-100 compared to Euclidean methods.
Out-Of-Distribution (OOD) detection is critical to deploy deep learning models in safety-critical applications. However, the inherent hierarchical concept structure of visual data, which is instrumental to OOD detection, is often poorly captured by conventional methods based on Euclidean geometry. This work proposes a metric framework that leverages the strengths of Hyperbolic geometry for OOD detection. Inspired by previous works that refine the decision boundary for OOD data with synthetic outliers, we extend this method to Hyperbolic space. Interestingly, we find that synthetic outliers do not benefit OOD detection in Hyperbolic space as they do in Euclidean space. Furthermore we explore the relationship between OOD detection performance and Hyperbolic embedding dimension, addressing practical concerns in resource-constrained environments. Extensive experiments show that our framework improves the FPR95 for OOD detection from 22\% to 15\% and from 49% to 28% on CIFAR-10 and CIFAR-100 respectively compared to Euclidean methods.