mlsanityData to 7 Oct 2026

Training Implicit Networks for Image Deblurring using Jacobian-Free Backpropagation

arXiv 2402.02065 ↗First posted 3 Feb 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent efforts in applying implicit networks to solve inverse problems in imaging have achieved competitive or even superior results when compared to feedforward networks. These implicit networks only require constant memory during backpropagation, regardless of the number of layers. However, they are not necessarily easy to train. Gradient calculations are computationally expensive because they require backpropagating through a fixed point. In particular, this process requires solving a large linear system whose size is determined by the number of features in the fixed point iteration. This paper explores a recently proposed method, Jacobian-free Backpropagation (JFB), a backpropagation scheme that circumvents such calculation, in the context of image deblurring problems. Our results show that JFB is comparable against fine-tuned optimization schemes, state-of-the-art (SOTA) feedforward networks, and existing implicit networks at a reduced computational cost.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 48 references that are in the map. First posted on arXiv 3 Feb 2024.

Builds on

23 of 48 references.

References · 23

  1. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  2. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  3. 2019Deep Equilibrium Modelscited by 603
  4. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
  5. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
  6. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
  7. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
  8. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  9. 2020Multiscale Deep Equilibrium Modelscited by 149
  10. 2021Deep Equilibrium Architectures for Inverse Problems in Imagingcited by 126
  11. 2019Implicit Deep Learningcited by 124
  12. 2020Monotone operator equilibrium networkscited by 100
11 more
  1. 2021JFB: Jacobian-Free Backpropagation for Implicit Networkscited by 84
  2. 2021On Training Implicit Modelscited by 73
  3. 2019Momentum-Net: Fast and convergent iterative neural network for inverse problemscited by 38
  4. 2021On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layerscited by 35
  5. 2021SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit modelscited by 26
  6. 2021Learning the optimal Tikhonov regularizer for inverse problemscited by 26
  7. 2021Learning Regularization Parameters of Inverse Problems via Deep Neural Networkscited by 19
  8. 2021Feasibility-based Fixed Point Networkscited by 17
  9. 2021Joint inference and input optimization in equilibrium networkscited by 15
  10. 2022Explainable AI via Learning to Optimizecited by 14
  11. 2018Enhanced CNN for image denoisingcited by 6

Built on by

Not cited yet.