English

A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection

Machine Learning 2021-06-18 v1

Abstract

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).

Keywords

Cite

@article{arxiv.2106.09022,
  title  = {A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection},
  author = {Jie Ren and Stanislav Fort and Jeremiah Liu and Abhijit Guha Roy and Shreyas Padhy and Balaji Lakshminarayanan},
  journal= {arXiv preprint arXiv:2106.09022},
  year   = {2021}
}