mlsanityData to 7 Oct 2026

Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysis

arXiv 2310.00133 ↗First posted 29 Sep 2023cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Plug-and-Play (PnP) priors is a widely-used family of methods for solving imaging inverse problems by integrating physical measurement models with image priors specified using image denoisers. PnP methods have been shown to achieve state-of-the-art performance when the prior is obtained using powerful deep denoisers. Despite extensive work on PnP, the topic of distribution mismatch between the training and testing data has often been overlooked in the PnP literature. This paper presents a set of new theoretical and numerical results on the topic of prior distribution mismatch and domain adaptation for alternating direction method of multipliers (ADMM) variant of PnP. Our theoretical result provides an explicit error bound for PnP-ADMM due to the mismatch between the desired denoiser and the one used for inference. Our analysis contributes to the work in the area by considering the mismatch under nonconvex data-fidelity terms and expansive denoisers. Our first set of numerical results quantifies the impact of the prior distribution mismatch on the performance of PnP-ADMM on the problem of image super-resolution. Our second set of numerical results considers a simple and effective domain adaption strategy that closes the performance gap due to the use of mismatched denoisers. Our results suggest the relative robustness of PnP-ADMM to prior distribution mismatch, while also showing that the performance gap can be significantly reduced with few training samples from the desired distribution.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 56 of its 74 references that are in the map. First posted on arXiv 29 Sep 2023.

Builds on

56 of 74 references.

References · 56

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  4. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  5. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  6. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
  7. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
  8. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
  9. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  10. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  11. 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 244
  12. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
38 more
  1. 2019Plug-and-Play Methods Provably Converge with Properly Trained Denoiserscited by 197
  2. 2021Deep Equilibrium Architectures for Inverse Problems in Imagingcited by 126
  3. 2019Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernelscited by 112
  4. 2017Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problemscited by 107
  5. 2021Gradient Step Denoiser for convergent Plug-and-Playcited by 107
  6. 2018Regularization by Denoising: Clarifications and New Interpretationscited by 102
  7. 2021Bayesian imaging using Plug & Play priors: when Langevin meets Tweediecited by 96
  8. 2022Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imagingcited by 94
  9. 2016A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstructioncited by 87
  10. 2017A Review of Convolutional Neural Networks for Inverse Problems in Imagingcited by 81
  11. 2018Denoising Prior Driven Deep Neural Network for Image Restorationcited by 80
  12. 2022Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularizationcited by 79
  13. 2015Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolationcited by 78
  14. 2020Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imagingcited by 78
  15. 2019Plug and play methods for magnetic resonance imaging (long version)cited by 75
  16. 2018An Online Plug-and-Play Algorithm for Regularized Image Reconstructioncited by 70
  17. 2019RARE: Image Reconstruction using Deep Priors Learned without Ground Truthcited by 64
  18. 2017Plug-and-Play Unplugged: Optimization Free Reconstruction using Consensus Equilibriumcited by 58
  19. 2021Measuring Robustness in Deep Learning Based Compressive Sensingcited by 53
  20. 2020Scalable Plug-and-Play ADMM with Convergence Guaranteescited by 49
  21. 2018prDeep: Robust Phase Retrieval with a Flexible Deep Networkcited by 46
  22. 2017Model based learning for accelerated, limited-view 3D photoacoustic tomographycited by 45
  23. 2023RxRx1: A Dataset for Evaluating Experimental Batch Correction Methodscited by 45
  24. 2020Provable Convergence of Plug-and-Play Priors with MMSE denoiserscited by 39
  25. 2020Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problemscited by 38
  26. 2022Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensingcited by 37
  27. 2020Convolutional Proximal Neural Networks and Plug-and-Play Algorithmscited by 36
  28. 2017Deep Mean-Shift Priors for Image Restorationcited by 34
  29. 2018A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimizationcited by 33
  30. 2019Block Coordinate Regularization by Denoisingcited by 33
  31. 2021Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Conditioncited by 22
  32. 2022Online Deep Equilibrium Learning for Regularization by Denoisingcited by 22
  33. 2023Frequency Disentangled Features in Neural Image Compressioncited by 14
  34. 2016Structured Nonconvex and Nonsmooth Optimization: Algorithms and Iteration Complexity Analysiscited by 13
  35. 2018Performance Analysis of Plug-and-Play ADMM: A Graph Signal Processing Perspectivecited by 13
  36. 2020A Fast Stochastic Plug-and-Play ADMM for Imaging Inverse Problemscited by 12
  37. 2015Fast Single Image Super-Resolutioncited by 10
  38. 2022Deep Model-Based Architectures for Inverse Problems under Mismatched Priorscited by 8

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 4.

10 papers.

  1. 2024Plug-and-Play image restoration with Stochastic deNOising REgularizationcited by 17
  2. 2025MRI Super-Resolution with Deep Learning: A Comprehensive Surveycited by 7
  3. 2024Plug-and-Play Priors as a Score-Based Methodcited by 5
  4. 2025Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Modelscited by 4
  5. 2024No-Clean-Reference Image Super-Resolution: Application to Electron Microscopycited by 3
  6. 2025Optimal Regularization Under Uncertainty: Distributional Robustness and Convexity Constraintscited by 0
  7. 2026A New Convergence Analysis of Plug-and-Play Proximal Gradient Descent Under Prior Mismatchcited by 0
  8. 2026Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstructioncited by 0
  9. 2026Plug-and-Play Volumetric Reconstruction for Compressive Sensing Light-Sheet Microscopycited by 0
  10. 2026Domain Adaptation of Mismatched Proximal Denoiser for Plug-and-Play Image Reconstructioncited by 0