# Out-of-Distribution Detection from Small Training Sets using Bayesian Neural Network Classifiers

arXiv: https://arxiv.org/abs/2510.06025 · HTML: https://mlsanity.com/paper/2510.06025/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Builds on (most cited first, 27 of 27)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Out-of-Distribution Detection with Deep Nearest Neighbors](https://mlsanity.com/paper/2204.06507/) (2022)
- [A Simple Baseline for Bayesian Uncertainty in Deep Learning](https://mlsanity.com/paper/1902.02476/) (2019)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [Laplace Redux -- Effortless Bayesian Deep Learning](https://mlsanity.com/paper/2106.14806/) (2021)
- [Understanding Measures of Uncertainty for Adversarial Example Detection](https://mlsanity.com/paper/1803.08533/) (2018)
- [Understanding Failures in Out-of-Distribution Detection with Deep Generative Models](https://mlsanity.com/paper/2107.06908/) (2021)
- [A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference](https://mlsanity.com/paper/1901.02731/) (2019)
- [Out-of-distribution Detection in Classifiers via Generation](https://mlsanity.com/paper/1910.04241/) (2019)
- [Specifying Weight Priors in Bayesian Deep Neural Networks with Empirical Bayes](https://mlsanity.com/paper/1906.05323/) (2019)
- [Out-Of-Distribution Detection Is Not All You Need](https://mlsanity.com/paper/2211.16158/) (2022)
- [Bayesian OOD detection with aleatoric uncertainty and outlier exposure](https://mlsanity.com/paper/2102.12959/) (2021)
- [Out of Distribution Data Detection Using Dropout Bayesian Neural Networks](https://mlsanity.com/paper/2202.08985/) (2022)
- [Prior choice affects ability of Bayesian neural networks to identify unknowns](https://mlsanity.com/paper/2005.04987/) (2020)
- [Adversarial Phenomenon in the Eyes of Bayesian Deep Learning](https://mlsanity.com/paper/1711.08244/) (2017)
- [Are Bayesian neural networks intrinsically good at out-of-distribution detection?](https://mlsanity.com/paper/2107.12248/) (2021)
- [Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox](https://mlsanity.com/paper/2406.09867/) (2024)

## Abstract (arXiv)

Out-of-Distribution (OOD) detection is critical to AI reliability and safety, yet in many practical settings, only a limited amount of training data is available. Bayesian Neural Networks (BNNs) are a promising class of model on which to base OOD detection, because they explicitly represent epistemic (i.e. model) uncertainty. In the small training data regime, BNNs are especially valuable because they can incorporate prior model information. We introduce a new family of Bayesian posthoc OOD scores based on expected logit vectors, and compare 5 Bayesian and 4 deterministic posthoc OOD scores. Experiments on MNIST and CIFAR-10 In-Distributions, with 5000 training samples or less, show that the Bayesian methods outperform corresponding deterministic methods.