Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms

Abstract

The linear inverse problem is fundamental to the development of various scientific areas. Innumerable attempts have been carried out to solve different variants of the linear inverse problem in different applications. Nowadays, the rapid development of deep learning provides a fresh perspective for solving the linear inverse problem, which has various well-designed network architectures results in state-of-the-art performance in many applications. In this paper, we present a comprehensive survey of the recent progress in the development of deep learning for solving various linear inverse problems. We review how deep learning methods are used in solving different linear inverse problems, and explore the structured neural network architectures that incorporate knowledge used in traditional methods. Furthermore, we identify open challenges and potential future directions along this research line.

arXiv comment60 pages; Publication in (Elsevier) Signal Processing, 2020

References in corpus (53)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Auto-Encoding Variational Bayes
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• TensorFlow: A system for large-scale machine learning
• ADADELTA: An Adaptive Learning Rate Method
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
• Message Passing Algorithms for Compressed Sensing
• One pixel attack for fooling deep neural networks
• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• Model-Based Compressive Sensing
• Deep Learning for Single Image Super-Resolution: A Brief Review
• Understanding deep learning requires rethinking generalization
• Medical image denoising using convolutional denoising autoencoders
• A Review of Convolutional Neural Networks for Inverse Problems in Imaging
• Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network
• AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
• CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)
• Data Augmentation by Pairing Samples for Images Classification
• Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
• Residual Dense Network for Image Super-Resolution
• Trainable ISTA for Sparse Signal Recovery
• Group-Sparse Signal Denoising: Non-Convex Regularization, Convex Optimization
• Learned D-AMP: Principled Neural Network based Compressive Image Recovery
• Staleness-aware Async-SGD for Distributed Deep Learning
• Learning the Number of Neurons in Deep Networks
• A GAMP Based Low Complexity Sparse Bayesian Learning Algorithm
• Why do deep convolutional networks generalize so poorly to small image transformations?
• Real-world Noisy Image Denoising: A New Benchmark
• Early stopping and non-parametric regression: An optimal data-dependent stopping rule
• Compressed Sensing with Deep Image Prior and Learned Regularization
• Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds
• Learned Convolutional Sparse Coding
• Distributed Compressive Sensing: A Deep Learning Approach
• DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factors
• Maximal Sparsity with Deep Networks?
• Recurrent Inference Machines for Solving Inverse Problems
• Fast Low-Rank Bayesian Matrix Completion with Hierarchical Gaussian Prior Models
• Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors
• Fast Beam Alignment for Millimeter Wave Communications: A Sparse Encoding and Phaseless Decoding Approach
• Joint Sensing Matrix and Sparsifying Dictionary Optimization for Tensor Compressive Sensing
• Restricted Isometry Property of Gaussian Random Projection for Finite Set of Subspaces
• Nonconvex Sparse Logistic Regression with Weakly Convex Regularization
• Forest Sparsity for Multi-channel Compressive Sensing
• Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation
• Cross-label Suppression: A Discriminative and Fast Dictionary Learning with Group Regularization
• From Bayesian Sparsity to Gated Recurrent Nets
• Deep Coupled-Representation Learning for Sparse Linear Inverse Problems with Side Information
• Conditioning of Random Block Subdictionaries with Applications to Block-Sparse Recovery and Regression
• A Multimodal Deep Network for the Reconstruction of T2W MR Images

Cited by in corpus (8)

• DAN-Net: Dual-Domain Adaptive-Scaling Non-local Network for CT Metal Artifact Reduction
• A Variational Bayesian Inference-Inspired Unrolled Deep Network for MIMO Detection
• Solving Sparse Linear Inverse Problems in Communication Systems: A Deep Learning Approach With Adaptive Depth
• Plug-and-Play Quantum Adaptive Denoiser for Deconvolving Poisson Noisy Images
• Fast hierarchical inversion for borehole resistivity measurements in high-angle and horizontal wells using ADNN-AMLM
• Solving inverse problems with deep neural networks driven by sparse signal decomposition in a physics-based dictionary
• On the Energy Self-Sustainability of IoT via Distributed Compressed Sensing
• A Plug-and-Play Priors Framework for Hyperspectral Unmixing