mlsanityData to 14 Oct 2026

Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection

arXiv 1912.05651 ↗First posted 11 Dec 2019cs.LG stat.MLcited by 35

Not on the map. Why?

Abstract (arXiv)

Despite their successes, deep neural networks may make unreliable predictions when faced with test data drawn from a distribution different to that of the training data, constituting a major problem for AI safety. While this has recently motivated the development of methods to detect such out-of-distribution (OoD) inputs, a robust solution is still lacking. We propose a new probabilistic, unsupervised approach to this problem based on a Bayesian variational autoencoder model, which estimates a full posterior distribution over the decoder parameters using stochastic gradient Markov chain Monte Carlo, instead of fitting a point estimate. We describe how information-theoretic measures based on this posterior can then be used to detect OoD inputs both in input space and in the model's latent space. We empirically demonstrate the effectiveness of our proposed approach.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 9; 2023: 8; 2024: 5; 2025: 6.

35 papers.

Sort:

By area:

  1. 2021Bayesian Learning via Neural Schr"odinger-F"ollmer Flowscited by 56
  2. 2021A Bit More Bayesian: Domain-Invariant Learning with Uncertaintycited by 27
  3. 2025Generative Uncertainty in Diffusion Modelscited by 23
  4. 2023Adversarial Bayesian Augmentation for Single-Source Domain Generalizationcited by 22
  5. 2022A Bayesian Framework for Digital Twin-Based Control, Monitoring, and Data Collection in Wireless Systemscited by 18
  6. 2022Bayesian Continual Learning via Spiking Neural Networkscited by 13
  7. 2022Multiple Importance Sampling ELBO and Deep Ensembles of Variational Approximationscited by 12
  8. 2023Fully Bayesian VIB-DeepSSMcited by 11
  9. 2021Model Selection for Bayesian Autoencoderscited by 10
  10. 2022Laplacian Autoencoders for Learning Stochastic Representationscited by 10
  11. 2021Improving Variational Autoencoder based Out-of-Distribution Detection for Embedded Real-time Applicationscited by 9
  12. 2022Robust Bayesian Learning for Reliable Wireless AI: Framework and Applicationscited by 9
23 more
  1. 2023Fully Bayesian Autoencoders with Latent Sparse Gaussian Processescited by 9
  2. 2021Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approachcited by 6
  3. 2021CVAD: A generic medical anomaly detector based on Cascade VAEcited by 6
  4. 2024Decoder ensembling for learned latent geometriescited by 6
  5. 2021Bayesian Autoencoders: Analysing and Fixing the Bernoulli likelihood for Out-of-Distribution Detectioncited by 4
  6. 2022Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detectioncited by 4
  7. 2022Leveraging variational autoencoders for multiple data imputationcited by 3
  8. 2022Do Bayesian Variational Autoencoders Know What They Don't Know?cited by 3
  9. 2025Can We Ignore Labels In Out of Distribution Detection?cited by 3
  10. 2025Digital Twin-based Out-of-Distribution Detection in Autonomous Vesselscited by 3
  11. 2022Digital Twin-Based Multiple Access Optimization and Monitoring via Model-Driven Bayesian Learningcited by 1
  12. 2023Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Componentscited by 1
  13. 2023Vacant Holes for Unsupervised Detection of the Outliers in Compact Latent Representationcited by 1
  14. 2023Bayesian Domain Invariant Learning via Posterior Generalization of Parameter Distributionscited by 1
  15. 2024A View on Out-of-Distribution Identification from a Statistical Testing Theory Perspectivecited by 1
  16. 2024Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matchingcited by 1
  17. 2023MSS-PAE: Saving Autoencoder-based Outlier Detection from Unexpected Reconstructioncited by 0
  18. 2023Uncertainty in Graph Contrastive Learning with Bayesian Neural Networkscited by 0
  19. 2024Forecasting infectious disease prevalence with associated uncertainty using neural networkscited by 0
  20. 2024Unsupervised Hybrid framework for ANomaly Detection (HAND) -- applied to Screening Mammogramcited by 0
  21. 2025Logit Disagreement: OoD Detection with Bayesian Neural Networkscited by 0
  22. 2025Bayesian generative models can flag performance loss, bias, and out-of-distribution image contentcited by 0
  23. 2025What Did I Learn? Operational Competence Assessment for AI-Based Trajectory Plannerscited by 0