mlsanityData to 14 Oct 2026

Out-of-Distribution Detection with a Single Unconditional Diffusion Model

arXiv 2405.11881 ↗First posted 20 May 2024cs.LG cs.AI stat.MLcited by 22

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Out-of-distribution (OOD) detection is a critical task in machine learning that seeks to identify abnormal samples. Traditionally, unsupervised methods utilize a deep generative model for OOD detection. However, such approaches require a new model to be trained for each inlier dataset. This paper explores whether a single model can perform OOD detection across diverse tasks. To that end, we introduce Diffusion Paths (DiffPath), which uses a single diffusion model originally trained to perform unconditional generation for OOD detection. We introduce a novel technique of measuring the rate-of-change and curvature of the diffusion paths connecting samples to the standard normal. Extensive experiments show that with a single model, DiffPath is competitive with prior work using individual models on a variety of OOD tasks involving different distributions. Our code is publicly available at https://github.com/clear-nus/diffpath.

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 40 of its 48 references that are in the map. First posted on arXiv 20 May 2024.

Builds on

40 of 48 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpainting20 Feb
  2. 2022Denoising diffusion models for out-of-distribution detection14 Nov

Other references · 38

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  7. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  9. 2023Consistency Modelscited by 1,822
  10. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  11. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  12. 2018Computational Optimal Transportcited by 780
26 more
  1. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  2. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  3. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  4. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  5. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  6. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  7. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  8. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  9. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  10. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  11. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  12. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  13. 2022Dual Diffusion Implicit Bridges for Image-to-Image Translationcited by 213
  14. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  15. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  16. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 134
  17. 2020Improved Contrastive Divergence Training of Energy Based Modelscited by 130
  18. 2022GENIE: Higher-Order Denoising Diffusion Solverscited by 127
  19. 2020VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Modelscited by 104
  20. 2018Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distancecited by 74
  21. 2020Density of States Estimation for Out-of-Distribution Detectioncited by 74
  22. 2023On Diffusion Modeling for Anomaly Detectioncited by 72
  23. 2022Understanding DDPM Latent Codes Through Optimal Transportcited by 45
  24. 2020Multiscale Score Matching for Out-of-Distribution Detectioncited by 36
  25. 2021Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?cited by 16
  26. 2023Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Modelscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 12; 2026: 9.

22 papers.

Sort:

By area:

  1. 2025Energy-Based Transformers are Scalable Learners and Thinkerscited by 31
  2. 2025Know When to Abstain: Optimal Selective Classification with Likelihood Ratioscited by 5
  3. 2025Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Modelscited by 4
  4. 2025EigenScore: OOD Detection using Covariance in Diffusion Modelscited by 4
  5. 2025InvAD: Inversion-based Reconstruction-Free Anomaly Detection with Diffusion Modelscited by 3
  6. 2025SCOPED: Score-Curvature Out-of-distribution Proximity Evaluator for Diffusioncited by 3
  7. 2025Zero-Shot Image Anomaly Detection Using Generative Foundation Modelscited by 2
  8. 2025Expert-Guided Diffusion Planner for Auto-Biddingcited by 2
  9. 2026Geometry over Density: Few-Shot Cross-Domain OOD Detectioncited by 2
  10. 2026GEPC: Group-Equivariant Posterior Consistency for Out-of-Distribution Detection in Diffusion Modelscited by 1
  11. 2026Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imagingcited by 1
  12. 2026Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuningcited by 1
10 more
  1. 2026The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spacescited by 1
  2. 2024Beyond Perceptual Distance: Discrepancy Assessment on Deep Representation for Out-of-Distribution Detection with Diffusion Modelcited by 0
  3. 2025Out-of-Distribution Detection in Medical Imaging via Diffusion Trajectoriescited by 0
  4. 2025Prompt Optimization Meets Subspace Representation Learning for Few-shot Out-of-Distribution Detectioncited by 0
  5. 2025Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectoriescited by 0
  6. 2025Out-of-Distribution Detection in Molecular Complexes via Diffusion Models for Irregular Graphscited by 0
  7. 2026Native Extrapolation Awareness in Flow-Based Conditional Generationcited by 0
  8. 2026Backbone-Equated Diffusion OOD via Sparse Internal Snapshotscited by 0
  9. 2026Tippett-minimum Fusion of Representation-space Diffusion Models for Multi-Encoder Out-of-Distribution Detectioncited by 0
  10. 2026KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024NODI: Out-Of-Distribution Detection with Noise from Diffusion
  2. 2024Enhancing OOD Detection Using Latent Diffusion
  3. 2024Exploiting Diffusion Prior for Out-of-Distribution Detection
  4. 2024Non-Linear Outlier Synthesis for Out-of-Distribution Detection
  5. 2025Probability Density from Latent Diffusion Models for Out-of-Distribution Detection
  6. 2025BOOD: Boundary-based Out-Of-Distribution Data Generation
  7. 2025Dream-Box: Object-wise Outlier Generation for Out-of-Distribution Detection
  8. 2024Deep Metric Learning-Based Out-of-Distribution Detection with Synthetic Outlier Exposure