Why Should we Combine Training and Post-Training Methods for Out-of-Distribution Detection?

TL;DR

This paper reviews recent OOD detection algorithms, categorizes them into training and post-training methods, and demonstrates that combining these approaches achieves state-of-the-art results in identifying out-of-distribution examples.

Contribution

It introduces a comprehensive review of OOD detection methods and empirically shows that combining training and post-training techniques enhances detection performance.

Findings

Combining training and post-training methods improves OOD detection accuracy.

The integrated approach achieves state-of-the-art results.

Post-training methods complement training algorithms effectively.

Abstract

Deep neural networks are known to achieve superior results in classification tasks. However, it has been recently shown that they are incapable to detect examples that are generated by a distribution which is different than the one they have been trained on since they are making overconfident prediction for Out-Of-Distribution (OOD) examples. OOD detection has attracted a lot of attention recently. In this paper, we review some of the most seminal recent algorithms in the OOD detection field, we divide those methods into training and post-training and we experimentally show how the combination of the former with the latter can achieve state-of-the-art results in the OOD detection task.