# Analysis of Confident-Classifiers for Out-of-distribution Detection

arXiv: https://arxiv.org/abs/1904.12220 · HTML: https://mlsanity.com/paper/1904.12220/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2019.

## Built on by (most cited first, 7 of 7)

- [Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data](https://mlsanity.com/paper/2212.09171/) (2022)
- [UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs](https://mlsanity.com/paper/2201.13279/) (2022)
- [SoK: Machine Learning Governance](https://mlsanity.com/paper/2109.10870/) (2021)
- [Distribution Awareness for AI System Testing](https://mlsanity.com/paper/2105.02540/) (2021)
- [FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detection](https://mlsanity.com/paper/2111.15487/) (2021)
- [Geometrically Constrained Outlier Synthesis](https://mlsanity.com/paper/2603.08413/) (2026)
- [ContraMap: Contrastive Uncertainty Mapping for Robot Environment Representation](https://mlsanity.com/paper/2603.27632/) (2026)

## Abstract (arXiv)

Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avoid classification errors. In the context of OOD detection for image classification, one of the recent approaches proposes training a classifier called "confident-classifier" by minimizing the standard cross-entropy loss on in-distribution samples and minimizing the KL divergence between the predictive distribution of OOD samples in the low-density regions of in-distribution and the uniform distribution (maximizing the entropy of the outputs). Thus, the samples could be detected as OOD if they have low confidence or high entropy. In this paper, we analyze this setting both theoretically and experimentally. We conclude that the resulting confident-classifier still yields arbitrarily high confidence for OOD samples far away from the in-distribution. We instead suggest training a classifier by adding an explicit "reject" class for OOD samples.