mlsanityData to 14 Oct 2026

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

arXiv 2510.06025 ↗First posted 7 Oct 2025cs.LG stat.MLcited by 0

Not on the map. Why?

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.

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

27 of 40 references.

References · 27

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  5. 2013Describing Textures in the Wildcited by 2,125
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  7. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  8. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  9. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 560
  10. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  11. 2015Variational Dropout and the Local Reparameterization Trickcited by 490
  12. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
15 more
  1. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  2. 2018Deep Learning for Classical Japanese Literaturecited by 422
  3. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 365
  4. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  5. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  6. 2019A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inferencecited by 51
  7. 2019Out-of-distribution Detection in Classifiers via Generationcited by 49
  8. 2019Specifying Weight Priors in Bayesian Deep Neural Networks with Empirical Bayescited by 32
  9. 2022Out-Of-Distribution Detection Is Not All You Needcited by 23
  10. 2021Bayesian OOD detection with aleatoric uncertainty and outlier exposurecited by 16
  11. 2022Out of Distribution Data Detection Using Dropout Bayesian Neural Networkscited by 15
  12. 2020Prior choice affects ability of Bayesian neural networks to identify unknownscited by 12
  13. 2017Adversarial Phenomenon in the Eyes of Bayesian Deep Learningcited by 11
  14. 2021Are Bayesian neural networks intrinsically good at out-of-distribution detection?cited by 10
  15. 2024Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradoxcited by 3

Built on by

Not cited yet.