mlsanityData to 14 Oct 2026

Out-of-Distribution Detection with Class Ratio Estimation

arXiv 2206.03955 ↗First posted 8 Jun 2022stat.ML cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Density-based Out-of-distribution (OOD) detection has recently been shown unreliable for the task of detecting OOD images. Various density ratio based approaches achieve good empirical performance, however methods typically lack a principled probabilistic modelling explanation. In this work, we propose to unify density ratio based methods under a novel framework that builds energy-based models and employs differing base distributions. Under our framework, the density ratio can be viewed as the unnormalized density of an implicit semantic distribution. Further, we propose to directly estimate the density ratio of a data sample through class ratio estimation. We report competitive results on OOD image problems in comparison with recent work that alternatively requires training of deep generative models for the task. Our approach enables a simple and yet effective path towards solving the OOD detection problem.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 35 of its 50 references that are in the map. First posted on arXiv 8 Jun 2022.

Builds on

35 of 50 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2013Auto-Encoding Variational Bayescited by 4,053
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  8. 2016Wide Residual Networkscited by 3,070
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  10. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  12. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
23 more
  1. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  2. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  3. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  4. 2016Pixel Recurrent Neural Networkscited by 816
  5. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  6. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  7. 2018Deep Learning for Classical Japanese Literaturecited by 422
  8. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 417
  9. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 364
  10. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 221
  11. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  12. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  13. 2020Telescoping Density-Ratio Estimationcited by 108
  14. 2020Generalized Energy Based Modelscited by 73
  15. 2020Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Samplingcited by 71
  16. 2016Amortised MAP Inference for Image Super-resolutioncited by 68
  17. 2020Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Featurescited by 64
  18. 2021Hierarchical VAEs Know What They Don't Knowcited by 58
  19. 2020Multiscale Score Matching for Out-of-Distribution Detectioncited by 36
  20. 2021On the Out-of-distribution Generalization of Probabilistic Image Modellingcited by 33
  21. 2019Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matricescited by 32
  22. 2019Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicalitycited by 31
  23. 2018Spread Divergencecited by 23

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 1.

4 papers.

  1. 2025DiffRatio: Training One-Step Diffusion Models Without Teacher Supervisioncited by 9
  2. 2022Falsehoods that ML researchers believe about OOD detectioncited by 8
  3. 2023SR-OOD: Out-of-Distribution Detection via Sample Repairingcited by 1
  4. 2024On the Detection of Anomalous or Out-Of-Distribution Data in Vision Models Using Statistical Techniquescited by 0