mlsanityData to 14 Oct 2026

Unsupervised 3D out-of-distribution detection with latent diffusion models

arXiv 2307.03777 ↗First posted 7 Jul 2023cs.CVcited by 22

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Methods for out-of-distribution (OOD) detection that scale to 3D data are crucial components of any real-world clinical deep learning system. Classic denoising diffusion probabilistic models (DDPMs) have been recently proposed as a robust way to perform reconstruction-based OOD detection on 2D datasets, but do not trivially scale to 3D data. In this work, we propose to use Latent Diffusion Models (LDMs), which enable the scaling of DDPMs to high-resolution 3D medical data. We validate the proposed approach on near- and far-OOD datasets and compare it to a recently proposed, 3D-enabled approach using Latent Transformer Models (LTMs). Not only does the proposed LDM-based approach achieve statistically significant better performance, it also shows less sensitivity to the underlying latent representation, more favourable memory scaling, and produces better spatial anomaly maps. Code is available at https://github.com/marksgraham/ddpm-ood

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 24 of its 34 references that are in the map. First posted on arXiv 7 Jul 2023.

Builds on

24 of 34 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Denoising diffusion models for out-of-distribution detection14 Nov

Other references · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  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. 2017Neural Discrete Representation Learningcited by 4,712
  7. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  8. 2020Rethinking Attention with Performerscited by 1,601
  9. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  10. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  11. 2021The Medical Segmentation Decathloncited by 628
  12. 2020Jukebox: A Generative Model for Musiccited by 542
11 more
  1. 2022MONAI: An open-source framework for deep learning in healthcarecited by 448
  2. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  3. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 422
  4. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  5. 2021Self-attention Does Not Need O(n2) Memorycited by 154
  6. 2018Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distancecited by 74
  7. 2021Hierarchical VAEs Know What They Don't Knowcited by 58
  8. 2022Transformer-based out-of-distribution detection for clinically safe segmentationcited by 16
  9. 2022Morphology-preserving Autoregressive 3D Generative Modelling of the Braincited by 15
  10. 2020Neuromorphologicaly-preserving Volumetric data encoding using VQ-VAEcited by 7
  11. 2023Cross Attention Transformers for Multi-modal Unsupervised Whole-Body PET Anomaly Detectioncited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 11; 2026: 4.

22 papers.

Sort:

By area:

  1. 2024Out-of-distribution Detection in Medical Image Analysis: A surveycited by 22
  2. 2025A Survey on Diffusion Models for Anomaly Detectioncited by 13
  3. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  4. 2025Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomizationcited by 6
  5. 2024Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolationscited by 5
  6. 2024Enhancing Reconstruction-Based Out-of-Distribution Detection in Brain MRI with Model and Metric Ensemblescited by 4
  7. 2025Unraveling Normal Anatomy via Fluid-Driven Anomaly Randomizationcited by 4
  8. 2024Denoising Diffusion Models for Anomaly Localization in Medical Imagescited by 3
  9. 2025MedSymmFlow: Bridging Generative Modeling and Classification in Medical Imaging through Symmetrical Flow Matchingcited by 2
  10. 2024Differentiable Score-Based Likelihoods: Learning CT Motion Compensation From Clean Imagescited by 1
  11. 2025Tumor-anchored deep feature random forests for out-of-distribution detection in lung cancer segmentationcited by 1
  12. 2026Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imagingcited by 1
10 more
  1. 2026Diffuse to Detect: Generative Diffusion Models for Unsupervised IC Anomaly Detectioncited by 1
  2. 2024LoGex: Improved tail detection of extremely rare histopathology classes via guided diffusioncited by 0
  3. 2024Exploring Out-of-distribution Detection for Sparse-view Computed Tomography with Diffusion Modelscited by 0
  4. 2025Investigating the Role of Bilateral Symmetry for Inpainting Brain MRIcited by 0
  5. 2025Unsupervised Out-of-Distribution Detection in Medical Imaging Using Multi-Exit Class Activation Maps and Feature Maskingcited by 0
  6. 2025CADD: Context aware disease deviations via restoration of brain images using normative conditional diffusion modelscited by 0
  7. 2025Generating healthy counterfactuals with denoising diffusion bridge modelscited by 0
  8. 2025Deep generative priors for 3D brain analysiscited by 0
  9. 2026Kidney Cancer Detection Using 3D-Based Latent Diffusion Modelscited by 0
  10. 2026Unsupervised Anomaly Detection for Image Dataset Quality Assurance in Multi-Center Breast MRIcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Out-of-Distribution Detection in Medical Imaging via Diffusion Trajectories
  2. 2025Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Review
  3. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Survey
  4. 2022Diffusion Denoising Process for Perceptron Bias in Out-of-distribution Detection
  5. 2022Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Models
  6. 2023Likelihood-based Out-of-Distribution Detection with Denoising Diffusion Probabilistic Models
  7. 2025Probability Density from Latent Diffusion Models for Out-of-Distribution Detection
  8. 2024NODI: Out-Of-Distribution Detection with Noise from Diffusion