mlsanityData to 7 Oct 2026

Task-Driven Uncertainty Quantification in Inverse Problems via Conformal Prediction

arXiv 2405.18527 ↗First posted 28 May 2024cs.CV eess.IVcited by 8

Not on the map. Why?

Abstract (arXiv)

In imaging inverse problems, one seeks to recover an image from missing/corrupted measurements. Because such problems are ill-posed, there is great motivation to quantify the uncertainty induced by the measurement-and-recovery process. Motivated by applications where the recovered image is used for a downstream task, such as soft-output classification, we propose a task-centered approach to uncertainty quantification. In particular, we use conformal prediction to construct an interval that is guaranteed to contain the task output from the true image up to a user-specified probability, and we use the width of that interval to quantify the uncertainty contributed by measurement-and-recovery. For posterior-sampling-based image recovery, we construct locally adaptive prediction intervals. Furthermore, we propose to collect measurements over multiple rounds, stopping as soon as the task uncertainty falls below an acceptable level. We demonstrate our methodology on accelerated magnetic resonance imaging (MRI): https://github.com/jwen307/TaskUQ.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 39 of its 64 references that are in the map. First posted on arXiv 28 May 2024.

Builds on

39 of 64 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2017On Calibration of Modern Neural Networkscited by 4,860
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  9. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  10. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  11. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  12. 2016Distribution-Free Predictive Inference For Regressioncited by 657
27 more
  1. 2019Conformalized Quantile Regressioncited by 620
  2. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  3. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 365
  4. 2021Score-based diffusion models for accelerated MRIcited by 308
  5. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  6. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 278
  7. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  8. 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 201
  9. 2022Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imagingcited by 107
  10. 2016Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreaucited by 83
  11. 2019Deep Learning Methods for Parallel Magnetic Resonance Image Reconstructioncited by 81
  12. 2018Deep Bayesian Inversioncited by 60
  13. 2023How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Controlcited by 50
  14. 2019Uncertainty Quantification in Deep MRI Reconstructioncited by 49
  15. 2022Physics-Driven Deep Learning for Computational Magnetic Resonance Imagingcited by 49
  16. 2022Improving Trustworthiness of AI Disease Severity Rating in Medical Imaging with Ordinal Conformal Prediction Setscited by 38
  17. 2022Conffusion: Confidence Intervals for Diffusion Modelscited by 33
  18. 2021Bayesian Uncertainty Estimation of Learned Variational MRI Reconstructioncited by 30
  19. 2019Reliable deep-learning-based phase imaging with uncertainty quantificationcited by 26
  20. 2022Semantic uncertainty intervals for disentangled latent spacescited by 22
  21. 2021Conditional Invertible Neural Networks for Medical Imagingcited by 19
  22. 2021Generative Flows with Invertible Attentionscited by 13
  23. 2022Uncertainty Quantification for Deep Unrolling-Based Computational Imagingcited by 10
  24. 2023A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imagingcited by 10
  25. 2020Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descentcited by 9
  26. 2022Technical Report (v1.0)--Pseudo-random Cartesian Sampling for Dynamic MRIcited by 8
  27. 2023A Plug-and-Play Method with Inpainting Network for Bayesian Uncertainty Quantification in Imagingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025Conformal Bounds on Full-Reference Image Quality for Imaging Inverse Problemscited by 2
  2. 2025Towards Distribution-Shift Uncertainty Estimation for Inverse Problems with Generative Priorscited by 1
  3. 2025Evaluating structural uncertainty in accelerated MRI: are voxelwise measures useful surrogates?cited by 0
  4. 2025QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problemscited by 0
  5. 2025Minimax Multi-Target Conformal Prediction with Applications to Imaging Inverse Problemscited by 0
  6. 2026KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problemscited by 0
  7. 2026SafeRestore: Detector-Relative Risk Certificates for Selective Industrial Image Restorationcited by 0
  8. 2026How Many Posterior Samples? Calibrated Stopping for Adaptive Sensingcited by 0