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

By Jie Jessie Ren, Stanislav Fort, J. Liu, Abhijit Guha Roy, Shreyas Padhy, Balaji Lakshminarayanan. 2021

310 citations recorded by the source corpus.

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).

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Anomaly & Outlier Detection

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Ziwei Liu
  2. Yixuan Li
  3. Kaiyang Zhou
  4. Jingkang Yang
  5. Bo Li
  6. Wayne Zhang
  7. Haoqi Wang
  8. Yiyou Sun

In Computer Vision and Pattern Recognition

  1. Ziwei Liu
  2. Luc Van Gool
  3. Chen Change Loy
  4. Xiaogang Wang
  5. Ming-Hsuan Yang
  6. Yu Qiao
  7. Dacheng Tao
  8. Trevor Darrell

In Anomaly & Outlier Detection

  1. Yixuan Li
  2. Yiyou Sun
  3. Xuefeng Du
  4. Ziwei Liu
  5. Jingkang Yang
  6. Stanislav Fort
  7. Dan Hendrycks
  8. Kaiyang Zhou

Citations in the corpus