mlsanityData to 7 Oct 2026

Bayesian Autoencoders: Analysing and Fixing the Bernoulli likelihood for Out-of-Distribution Detection

arXiv 2107.13304 ↗First posted 28 Jul 2021cs.LG stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

After an autoencoder (AE) has learnt to reconstruct one dataset, it might be expected that the likelihood on an out-of-distribution (OOD) input would be low. This has been studied as an approach to detect OOD inputs. Recent work showed this intuitive approach can fail for the dataset pairs FashionMNIST vs MNIST. This paper suggests this is due to the use of Bernoulli likelihood and analyses why this is the case, proposing two fixes: 1) Compute the uncertainty of likelihood estimate by using a Bayesian version of the AE. 2) Use alternative distributions to model the likelihood.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 9 of its 17 references that are in the map. First posted on arXiv 28 Jul 2021.

Builds on

9 of 17 references.

References · 9

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2015Cyclical Learning Rates for Training Neural Networkscited by 627
  3. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  4. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  5. 2014Stochastic Gradient Hamiltonian Monte Carlocited by 341
  6. 2019Quality of Uncertainty Quantification for Bayesian Neural Network Inferencecited by 58
  7. 2018An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videoscited by 45
  8. 2019The continuous Bernoulli: fixing a pervasive error in variational autoencoderscited by 40
  9. 2019Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detectioncited by 35

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 1; 2023: 1.

4 papers.

  1. 2021Robust outlier detection by de-biasing VAE likelihoodscited by 8
  2. 2022Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detectioncited by 4
  3. 2021Coalitional Bayesian Autoencoders -- Towards explainable unsupervised deep learningcited by 0
  4. 2023MSS-PAE: Saving Autoencoder-based Outlier Detection from Unexpected Reconstructioncited by 0