mlsanityData to 7 Oct 2026

SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees

arXiv 2101.09379 ↗First posted 22 Jan 2021eess.IV cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Deep unfolding networks have recently gained popularity in the context of solving imaging inverse problems. However, the computational and memory complexity of data-consistency layers within traditional deep unfolding networks scales with the number of measurements, limiting their applicability to large-scale imaging inverse problems. We propose SGD-Net as a new methodology for improving the efficiency of deep unfolding through stochastic approximations of the data-consistency layers. Our theoretical analysis shows that SGD-Net can be trained to approximate batch deep unfolding networks to an arbitrary precision. Our numerical results on intensity diffraction tomography and sparse-view computed tomography show that SGD-Net can match the performance of the batch network at a fraction of training and testing complexity.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 45 of its 91 references that are in the map. First posted on arXiv 22 Jan 2021.

Builds on

45 of 91 references.

References · 45

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2018Group Normalizationcited by 1,514
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  5. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,140
  6. 2015Cyclical Learning Rates for Training Neural Networkscited by 627
  7. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
  8. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
  9. 2019Why gradient clipping accelerates training: A theoretical justification for adaptivitycited by 335
  10. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
  11. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  12. 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
33 more
  1. 2017Learned Primal-dual Reconstructioncited by 251
  2. 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 244
  3. 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 231
  4. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
  5. 2019Plug-and-Play Methods Provably Converge with Properly Trained Denoiserscited by 197
  6. 2017Solving ill-posed inverse problems using iterative deep neural networkscited by 145
  7. 2017Non-convex Optimization for Machine Learningcited by 132
  8. 2018Regularization by Denoising: Clarifications and New Interpretationscited by 102
  9. 2016A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstructioncited by 87
  10. 2017Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CTcited by 87
  11. 2019DeepRED: Deep Image Prior Powered by REDcited by 84
  12. 2017A Review of Convolutional Neural Networks for Inverse Problems in Imagingcited by 81
  13. 2015Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolationcited by 78
  14. 2017CNN-Based Projected Gradient Descent for Consistent Image Reconstructioncited by 75
  15. 2019Plug and play methods for magnetic resonance imaging (long version)cited by 75
  16. 2013Accelerated Gradient Methods for Nonconvex Nonlinear and Stochastic Programmingcited by 74
  17. 2018An Online Plug-and-Play Algorithm for Regularized Image Reconstructioncited by 70
  18. 2019RARE: Image Reconstruction using Deep Priors Learned without Ground Truthcited by 64
  19. 2017Plug-and-Play Unplugged: Optimization Free Reconstruction using Consensus Equilibriumcited by 58
  20. 2018prDeep: Robust Phase Retrieval with a Flexible Deep Networkcited by 46
  21. 2017Model based learning for accelerated, limited-view 3D photoacoustic tomographycited by 45
  22. 2020Provable Convergence of Plug-and-Play Priors with MMSE denoiserscited by 39
  23. 2019Momentum-Net: Fast and convergent iterative neural network for inverse problemscited by 38
  24. 2019Block Coordinate Regularization by Denoisingcited by 33
  25. 2015On learning optimized reaction diffusion processes for effective image restorationcited by 25
  26. 2019Memory-efficient Learning for Large-scale Computational Imaging -- NeurIPS deep inverse workshopcited by 17
  27. 2019SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priorscited by 16
  28. 2019Online Regularization by Denoising with Applications to Phase Retrievalcited by 12
  29. 2018Efficient and accurate inversion of multiple scattering with deep learningcited by 10
  30. 2019BCD-Net for Low-dose CT Reconstruction: Acceleration, Convergence, and Generalizationcited by 7
  31. 2018High-throughput intensity diffraction tomography with a computational microscopecited by 6
  32. 2015Learning optimal nonlinearities for iterative thresholding algorithmscited by 4
  33. 2018Learning-based Image Reconstruction via Parallel Proximal Algorithmcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 4; 2023: 5; 2024: 2; 2025: 2; 2026: 1.

18 papers.

Sort:

By area:

  1. 2022DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstructioncited by 73
  2. 2025InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciencescited by 67
  3. 2021Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Conditioncited by 22
  4. 2022Online Deep Equilibrium Learning for Regularization by Denoisingcited by 22
  5. 2021End-to-End Sequential Sampling and Reconstruction for MRIcited by 13
  6. 2021Deformation-Compensated Learning for Image Reconstruction without Ground Truthcited by 9
  7. 2022StyleAM: Perception-Oriented Unsupervised Domain Adaption for Non-reference Image Quality Assessmentcited by 9
  8. 2023PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstructioncited by 9
  9. 2023Stochastic Unrolled Federated Learningcited by 6
  10. 2022GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstructioncited by 3
  11. 2023Learning Task-Specific Strategies for Accelerated MRIcited by 3
  12. 2024Swap-Net: A Memory-Efficient 2.5D Network for Sparse-View 3D Cone Beam CT Reconstructioncited by 3
6 more
  1. 2026Stochastic Generative Plug-and-Play Priorscited by 3
  2. 2023Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuningcited by 2
  3. 2021Photothermal-SR-Net: A Customized Deep Unfolding Neural Network for Photothermal Super Resolution Imagingcited by 1
  4. 2024Pivotal Auto-Encoder via Self-Normalizing ReLUcited by 1
  5. 2023MB-DECTNet: A Model-Based Unrolled Network for Accurate 3D DECT Reconstructioncited by 0
  6. 2025ResPF: Residual Poisson Flow for Efficient and Physically Consistent Sparse-View CT Reconstructioncited by 0