Contrastive Training for Improved Out-of-Distribution Detection

By Jim Winkens, Rudy Bunel, Abhijit Guha Roy, Robert Stanforth, Vivek Natarajan, J. Ledsam, Patricia MacWilliams, Pushmeet Kohli, Alan Karthikesalingam, Simon A. A. Kohl and 3 more. 2020

271 citations recorded by the source corpus.

Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investigates the use of contrastive training to boost OOD detection performance. Unlike leading methods for OOD detection, our approach does not require access to examples labeled explicitly as OOD, which can be difficult to collect in practice. We show in extensive experiments that contrastive training significantly helps OOD detection performance on a number of common benchmarks. By introducing and employing the Confusion Log Probability (CLP) score, which quantifies the difficulty of the OOD detection task by capturing the similarity of inlier and outlier datasets, we show that our method especially improves performance in the `near OOD' classes -- a particularly challenging setting for previous methods.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, 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. Bing Liu
  2. Yixuan Li
  3. Wojciech Samek
  4. Yoshua Bengio
  5. Sergey Levine
  6. Stanislav Fort
  7. Grgoire Montavon
  8. Mohit Bansal

In Representation & Self-Supervised Learning

  1. Bing Liu
  2. Yixuan Li
  3. Sepideh Esmaeilpour
  4. Wojciech Samek
  5. Lei Shu
  6. Grgoire Montavon
  7. Jinwoo Shin
  8. Negar Rostamzadeh

In Anomaly & Outlier Detection

  1. Stanislav Fort
  2. Yixuan Li
  3. Rui Huang
  4. Mung Chiang
  5. Sepideh Esmaeilpour
  6. Prateek Mittal
  7. Thomas G. Dietterich
  8. Lei Shu

Citations in the corpus