NETT: solving inverse problems with deep neural networks

DOI10.1088/1361-6420/ab6d57zbMath1456.65038arXiv1803.00092OpenAlexW3002289736MaRDI QIDQ5113628

Markus Haltmeier, Stephan Antholzer, Housen Li, Johannes Schwab

Publication date: 15 June 2020

Published in: Inverse Problems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1803.00092

zbMATH Keywords

convergence analysisinverse problemsimage reconstructionconvolutional neural networksdeep learningabsolute Bregman distance

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Artificial neural networks and deep learning (68T07) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Numerical solution to inverse problems in abstract spaces (65J22)

Related Items (max. 100)

Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method ⋮ Adversarially learned iterative reconstruction for imaging inverse problems ⋮ The numerics of phase retrieval ⋮ Analytic continuation of noisy data using Adams Bashforth residual neural network ⋮ Regularization theory of the analytic deep prior approach ⋮ Deep learning for inverse problems. Abstracts from the workshop held March 7--13, 2021 (hybrid meeting) ⋮ Deep-learning based discovery of partial differential equations in integral form from sparse and noisy data ⋮ Deep Learning--Based Dictionary Learning and Tomographic Image Reconstruction ⋮ Adaptive Tikhonov strategies for stochastic ensemble Kalman inversion ⋮ A Generative Variational Model for Inverse Problems in Imaging ⋮ Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks ⋮ Divide-and-conquer DNN approach for the inverse point source problem using a few single frequency measurements ⋮ Deep learning methods for partial differential equations and related parameter identification problems ⋮ Relaxation approach for learning neural network regularizers for a class of identification problems ⋮ Limitations of neural network training due to numerical instability of backpropagation ⋮ A direct sampling-based deep learning approach for inverse medium scattering problems ⋮ Invertible residual networks in the context of regularization theory for linear inverse problems ⋮ Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling ⋮ On obtaining initial approximation for the full wave inversion problem using convolutional neural network ⋮ Regularising inverse problems with generative machine learning models ⋮ TNet: A Model-Constrained Tikhonov Network Approach for Inverse Problems ⋮ Rethinking the ill-posedness of the spectral function reconstruction -- why is it fundamentally hard and how artificial neural networks can help ⋮ Convergence analysis of critical point regularization with non-convex regularizers ⋮ Application of machine learning regression models to inverse eigenvalue problems ⋮ Numerical methods for identifying the diffusion coefficient in a nonlinear elliptic equation ⋮ Linearized inverse Schrödinger potential problem with partial data and its deep neural network inversion ⋮ Data-consistent neural networks for solving nonlinear inverse problems ⋮ Computed tomography reconstruction using deep image prior and learned reconstruction methods ⋮ Numerical solution of inverse problems by weak adversarial networks ⋮ Data driven regularization by projection ⋮ Deep synthesis network for regularizing inverse problems ⋮ Big in Japan: regularizing networks for solving inverse problems ⋮ Learning regularization parameters of inverse problems via deep neural networks ⋮ NETT ⋮ Solving inverse problems using data-driven models ⋮ Estimating adsorption isotherm parameters in chromatography via a virtual injection promoting double feed-forward neural network ⋮ Hybrid projection methods for large-scale inverse problems with mixed Gaussian priors ⋮ On Learned Operator Correction in Inverse Problems ⋮ Strong Solutions for PDE-Based Tomography by Unsupervised Learning ⋮ Learnable Descent Algorithm for Nonsmooth Nonconvex Image Reconstruction ⋮ Shared Prior Learning of Energy-Based Models for Image Reconstruction ⋮ Deep learning architectures for nonlinear operator functions and nonlinear inverse problems

Uses Software

• UNLocBoX
• U-Net

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The Little Engine that Could: Regularization by Denoising (RED)
• The residual method for regularizing ill-posed problems
• Variational methods in imaging
• Totally convex functions for fixed points computation and infinite dimensional optimization
• A Tikhonov-based projection iteration for nonlinear ill-posed problems with sparsity con\-straints
• Mathematical Methods in Image Reconstruction
• Proximal Splitting Methods in Signal Processing
• Generalized Bregman distances and convergence rates for non-convex regularization methods
• Necessary and sufficient conditions for linear convergence of ℓ1-regularization
• Mathematics of thermoacoustic tomography
• Convergence rates and source conditions for Tikhonov regularization with sparsity constraints
• Sparse regularization with l ^q penalty term
• Orthonormal bases of compactly supported wavelets
• New tight frames of curvelets and optimal representations of objects with piecewise C² singularities
• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
• Solving ill-posed inverse problems using iterative deep neural networks
• Sampling Conditions for the Circular Radon Transform
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
• Convergence rates of convex variational regularization
• Photoacoustic and Thermoacoustic Tomography: Image Formation Principles
• Deep learning for photoacoustic tomography from sparse data
• Dictionary Identification—Sparse Matrix-Factorization via $\ell_1$-Minimization
• Inversion of Spherical Means and the Wave Equation in Even Dimensions
• Temporal back-projection algorithms for photoacoustic tomography with integrating line detectors

This page was built for publication: NETT: solving inverse problems with deep neural networks