mlsanityData to 14 Oct 2026

KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problems

arXiv 2605.31596 ↗First posted 29 May 2026cs.CV cs.LGcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Diffusion models have shown promising performance as data-driven priors for computational imaging, as well as some capacity to detect out-of-distribution (OOD) images. However, existing approaches to OOD detection often require some knowledge of the shifted distribution, fail to detect subtle or localized distribution shifts, and operate on full images, rather than the indirect measurements available in inverse problems. We propose an OOD detection metric based on the Kullback-Leibler divergence between the diffusion prior and the posterior distribution, that (i) does not require any calibration data or knowledge of the shifted distribution, and (ii) can detect whole images as OOD as well as localize OOD patches within an image. Experimentally, we show that this metric can detect subtle yet semantically meaningful distribution shifts, such as the shift from healthy liver CT scans to those with tumors, and generalizes across different types of diffusion models, datasets, and inverse problems. Our code can be found at https://github.com/voilalab/KLIP.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 34 of its 48 references that are in the map. First posted on arXiv 29 May 2026.

Builds on

34 of 48 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025EigenScore: OOD Detection using Covariance in Diffusion Models8 Oct
  2. 2024Out-of-Distribution Detection with a Single Unconditional Diffusion Model20 May
  3. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Models15 Nov

Other references · 31

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  6. 2022Denoising Diffusion Restoration Modelscited by 963
  7. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  8. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  9. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  10. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  11. 2022Generative Modelling With Inverse Heat Dissipationcited by 167
  12. 2022Diffusion Probabilistic Model Made Slimcited by 121
19 more
  1. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  2. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  3. 2022Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imagingcited by 107
  4. 2024Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priorscited by 97
  5. 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstructioncited by 73
  6. 2024DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Modelscited by 61
  7. 2023Label-Free Liver Tumor Segmentationcited by 56
  8. 2023How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Controlcited by 50
  9. 2024Tutorial on Diffusion Models for Imaging and Visioncited by 49
  10. 2024MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detectioncited by 35
  11. 2022Conffusion: Confidence Intervals for Diffusion Modelscited by 33
  12. 2024Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problemscited by 20
  13. 2023Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problemscited by 17
  14. 2023Limitations of Out-of-Distribution Detection in 3D Medical Image Segmentationcited by 11
  15. 2024Uncertainty Quantification for Forward and Inverse Problems of PDEs via Latent Global Evolutioncited by 8
  16. 2024Task-Driven Uncertainty Quantification in Inverse Problems via Conformal Predictioncited by 8
  17. 2024CUQDS: Conformal Uncertainty Quantification under Distribution Shift for Trajectory Predictioncited by 5
  18. 2025Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Modelscited by 4
  19. 2023Randomized Physics-Informed Machine Learning for Uncertainty Quantification in High-Dimensional Inverse Problemscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Out-of-Distribution Detection in Medical Imaging via Diffusion Trajectories
  2. 2024Exploring Out-of-distribution Detection for Sparse-view Computed Tomography with Diffusion Models
  3. 2024Exploiting Diffusion Prior for Out-of-Distribution Detection
  4. 2025Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories
  5. 2025GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
  6. 2023Dual Conditioned Diffusion Models for Out-Of-Distribution Detection: Application to Fetal Ultrasound Videos
  7. 2024Patch-Based Diffusion Models Beat Whole-Image Models for Mismatched Distribution Inverse Problems
  8. 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpainting