mlsanityData to 7 Oct 2026

Robustness of Deep Equilibrium Architectures to Changes in the Measurement Model

arXiv 2211.00531 ↗First posted 1 Nov 2022eess.IV cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Deep model-based architectures (DMBAs) are widely used in imaging inverse problems to integrate physical measurement models and learned image priors. Plug-and-play priors (PnP) and deep equilibrium models (DEQ) are two DMBA frameworks that have received significant attention. The key difference between the two is that the image prior in DEQ is trained by using a specific measurement model, while that in PnP is trained as a general image denoiser. This difference is behind a common assumption that PnP is more robust to changes in the measurement models compared to DEQ. This paper investigates the robustness of DEQ priors to changes in the measurement models. Our results on two imaging inverse problems suggest that DEQ priors trained under mismatched measurement models outperform image denoisers.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 12 of its 27 references that are in the map. First posted on arXiv 1 Nov 2022.

Builds on

12 of 27 references.

References · 12

  1. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  2. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  3. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
  4. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
  5. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
  6. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  7. 2021Deep Equilibrium Architectures for Inverse Problems in Imagingcited by 126
  8. 2021Gradient Step Denoiser for convergent Plug-and-Playcited by 107
  9. 2017A Review of Convolutional Neural Networks for Inverse Problems in Imagingcited by 81
  10. 2022Online Deep Equilibrium Learning for Regularization by Denoisingcited by 22
  11. 2020Model Adaptation for Inverse Problems in Imagingcited by 20
  12. 2022Deep Model-Based Architectures for Inverse Problems under Mismatched Priorscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024Solving Inverse Problems with Model Mismatch using Untrained Neural Networks within Model-based Architecturescited by 3
  2. 2025Recovering Pulse Waves from Video Using Deep Unrolling and Deep Equilibrium Modelscited by 2
  3. 2024Robustness and Exploration of Variational and Machine Learning Approaches to Inverse Problems: An Overviewcited by 1
  4. 2026Lipschitz Multiscale Deep Equilibrium Models: A Theoretically Guaranteed and Accelerated Approachcited by 1