A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection
Mahalanobis distance (MD) is a simple and popular post-processing method for detecting out-of-distribution (OOD) inputs in neural networks. We analyze its failure modes for near-OOD detection and propose a simple fix called relative Mahalanobis distance (RMD) which improves performance and is more robust to hyperparameter choice. On a wide selection of challenging vision, language, and biology OOD benchmarks (CIFAR-100 vs CIFAR-10, CLINC OOD intent detection, Genomics OOD), we show that RMD meaningfully improves upon MD performance (by up to 15% AUROC on genomics OOD).
Code (4)
Tasks
Intent DetectionOut-of-Distribution DetectionOut of Distribution (OOD) DetectionSimilar Papers 제목 키워드 기반
MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
Out-of-distribution (OOD) detection is a critical component for ensuring the reliability of deep neural networks in safety-critical applications. In this work, we present a key empirical observation: for in-distribution …
Infinite-dimensional Mahalanobis Distance with Applications to Kernelized Novelty Detection
The Mahalanobis distance is a classical tool used to measure the covariance-adjusted distance between points in $\bbR^d$. In this work, we extend the concept of Mahalanobis distance to separable Banach spaces by reinterp…
Anomaly DetectionNovelty DetectionSemi-supervised Anomaly DetectionSupervised Anomaly Detection+2Adversarial vulnerability of powerful near out-of-distribution detection
There has been a significant progress in detecting out-of-distribution (OOD) inputs in neural networks recently, primarily due to the use of large models pretrained on large datasets, and an emerging use of multi-modalit…
Adversarial RobustnessOut-of-Distribution DetectionOut of Distribution (OOD) DetectionA Bayesian Nonparametric Perspective on Mahalanobis Distance for Out of Distribution Detection
Bayesian nonparametric methods are naturally suited to the problem of out-of-distribution (OOD) detection. However, these techniques have largely been eschewed in favor of simpler methods based on distances between pre-t…
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionA Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space
Detecting out-of-domain (OOD) input intents is critical in the task-oriented dialog system. Different from most existing methods that rely heavily on manually labeled OOD samples, we focus on the unsupervised OOD detecti…
Out of Distribution (OOD) Detection