mlsanityData to 14 Oct 2026

Denoising diffusion models for out-of-distribution detection

arXiv 2211.07740 ↗First posted 14 Nov 2022cs.LG cs.CVcited by 104

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Out-of-distribution detection is crucial to the safe deployment of machine learning systems. Currently, unsupervised out-of-distribution detection is dominated by generative-based approaches that make use of estimates of the likelihood or other measurements from a generative model. Reconstruction-based methods offer an alternative approach, in which a measure of reconstruction error is used to determine if a sample is out-of-distribution. However, reconstruction-based approaches are less favoured, as they require careful tuning of the model's information bottleneck - such as the size of the latent dimension - to produce good results. In this work, we exploit the view of denoising diffusion probabilistic models (DDPM) as denoising autoencoders where the bottleneck is controlled externally, by means of the amount of noise applied. We propose to use DDPMs to reconstruct an input that has been noised to a range of noise levels, and use the resulting multi-dimensional reconstruction error to classify out-of-distribution inputs. We validate our approach both on standard computer-vision datasets and on higher dimension medical datasets. Our approach outperforms not only reconstruction-based methods, but also state-of-the-art generative-based approaches. Code is available at https://github.com/marksgraham/ddpm-ood.

Key facts. Cited by 104 papers in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 32 of its 54 references that are in the map. First posted on arXiv 14 Nov 2022.

Builds on

32 of 54 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  9. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  10. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  11. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  12. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
20 more
  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  2. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  3. 2021Score-based Generative Modeling in Latent Spacecited by 636
  4. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
  5. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 532
  6. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  7. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  8. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  9. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 334
  10. 2014One weird trick for parallelizing convolutional neural networkscited by 264
  11. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  12. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Qualitycited by 182
  13. 2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
  14. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  15. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  16. 2022GENIE: Higher-Order Denoising Diffusion Solverscited by 127
  17. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  18. 2018Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distancecited by 74
  19. 2020Density of States Estimation for Out-of-Distribution Detectioncited by 74
  20. 2021Hierarchical VAEs Know What They Don't Knowcited by 58

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 20; 2024: 30; 2025: 27; 2026: 27.

104 papers.

Sort:

By area:

  1. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  2. 2024Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progresscited by 69
  3. 2023Generative AI for Medical Imaging: extending the MONAI Frameworkcited by 68
  4. 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpaintingcited by 59
  5. 2023Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection through Automatic Diffusion Modelscited by 50
  6. 2023Patched Diffusion Models for Unsupervised Anomaly Detection in Brain MRIcited by 45
  7. 2023DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Modelscited by 26
  8. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 26
  9. 2023Unsupervised 3D out-of-distribution detection with latent diffusion modelscited by 22
  10. 2024A Geometric Explanation of the Likelihood OOD Detection Paradoxcited by 22
  11. 2024Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Modelscited by 22
  12. 2024Out-of-distribution Detection in Medical Image Analysis: A surveycited by 22
38 more
  1. 2024Out-of-Distribution Detection with a Single Unconditional Diffusion Modelcited by 22
  2. 2025Secure On-Device Video OOD Detection Without Backpropagationcited by 19
  3. 2023Guided Reconstruction with Conditioned Diffusion Models for Unsupervised Anomaly Detection in Brain MRIscited by 18
  4. 2023On the use of Mahalanobis distance for out-of-distribution detection with neural networks for medical imagingcited by 15
  5. 2024Detecting Out-Of-Distribution Earth Observation Images with Diffusion Modelscited by 14
  6. 2025Out-of-Distribution Detection Methods Answer the Wrong Questionscited by 14
  7. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  8. 2023Dual Conditioned Diffusion Models for Out-Of-Distribution Detection: Application to Fetal Ultrasound Videoscited by 12
  9. 2024Towards Understanding and Quantifying Uncertainty for Text-to-Image Generationcited by 11
  10. 2023Likelihood-based Out-of-Distribution Detection with Denoising Diffusion Probabilistic Modelscited by 10
  11. 2025MAD-AD: Masked Diffusion for Unsupervised Brain Anomaly Detectioncited by 10
  12. 2024Diffusion for Out-of-Distribution Detection on Road Scenes and Beyondcited by 9
  13. 2026From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detectioncited by 9
  14. 2024GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Modelcited by 6
  15. 2025Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representationscited by 6
  16. 2025Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomizationcited by 6
  17. 2023DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifierscited by 5
  18. 2023AuthentiGPT: Detecting Machine-Generated Text via Black-Box Language Models Denoisingcited by 5
  19. 2024Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolationscited by 5
  20. 2024Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakescited by 5
  21. 2024Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detectioncited by 5
  22. 2025Test-Time Canonicalization by Foundation Models for Robust Perceptioncited by 5
  23. 2024Feature Density Estimation for Out-of-Distribution Detection via Normalizing Flowscited by 4
  24. 2024Prompt-Softbox-Prompt: A Free-Text Embedding Control for Image Editingcited by 4
  25. 2024Can Your Generative Model Detect Out-of-Distribution Covariate Shift?cited by 4
  26. 2025Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Modelscited by 4
  27. 2025EigenScore: OOD Detection using Covariance in Diffusion Modelscited by 4
  28. 2023Neuro-symbolic Empowered Denoising Diffusion Probabilistic Models for Real-time Anomaly Detection in Industry 4.0cited by 3
  29. 2023Adversarial Denoising Diffusion Model for Unsupervised Anomaly Detectioncited by 3
  30. 2025DOSE3 : Diffusion-based Out-of-distribution detection on SE(3) trajectoriescited by 3
  31. 2025SCOPED: Score-Curvature Out-of-distribution Proximity Evaluator for Diffusioncited by 3
  32. 2026Dreaming the Unseen: World Model-regularized Diffusion Policy for Out-of-Distribution Robustnesscited by 3
  33. 2026YoCausal: How Far is Video Generation from World Model? A Causality Perspectivecited by 3
  34. 2023Anomaly Detection in Networks via Score-Based Generative Modelscited by 2
  35. 2023Histogram- and Diffusion-Based Medical Out-of-Distribution Detectioncited by 2
  36. 2024Approximations to the Fisher Information Metric of Deep Generative Models for Out-Of-Distribution Detectioncited by 2
  37. 2025Zero-Shot Image Anomaly Detection Using Generative Foundation Modelscited by 2
  38. 2025Probability Density from Latent Diffusion Models for Out-of-Distribution Detectioncited by 2

50 most cited of 104 All 104 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
  2. 2026Blind denoising diffusion models and the blessings of dimensionality
  3. 2022Diffusion Denoising Process for Perceptron Bias in Out-of-distribution Detection
  4. 2021Improved Denoising Diffusion Probabilistic Models
  5. 2025Diffusion Models: A Mathematical Introduction
  6. 2022Diffusion Models in Vision: A Survey
  7. 2022Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models
  8. 2023Fast Inference in Denoising Diffusion Models via MMD Finetuning