DRIP: deep regularizers for inverse problems
From MaRDI portal
Publication:6141552
Numerical optimization and variational techniques (65K10) Artificial neural networks and deep learning (68T07) Computational aspects of data analysis and big data (68T09) Large-scale problems in mathematical programming (90C06) Computing methodologies for image processing (68U10) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20)
Abstract: Inverse problems are mathematically ill-posed. Thus, given some (noisy) data, there is more than one solution that fits the data. In recent years, deep neural techniques that find the most appropriate solution, in the sense that it contains a-priori information, were developed. However, they suffer from several shortcomings. First, most techniques cannot guarantee that the solution fits the data at inference. Second, while the derivation of the techniques is inspired by the existence of a valid scalar regularization function, such techniques do not in practice rely on such a function, and therefore veer away from classical variational techniques. In this work we introduce a new family of neural regularizers for the solution of inverse problems. These regularizers are based on a variational formulation and are guaranteed to fit the data. We demonstrate their use on a number of highly ill-posed problems, from image deblurring to limited angle tomography.
Recommendations
- Big in Japan: regularizing networks for solving inverse problems
- Learned regularizers for inverse problems
- Regularization by architecture: a deep prior approach for inverse problems
- NETT: solving inverse problems with deep neural networks
- Regularising inverse problems with generative machine learning models
Cites work
- scientific article; zbMATH DE number 3181381 (Why is no real title available?)
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- scientific article; zbMATH DE number 936298 (Why is no real title available?)
- A distribution-free M-estimator of multivariate scatter
- A multilevel framework for sparse optimization with application to inverse covariance estimation and logistic regression
- Convergence Results for a Coordinate Projection Method Applied to Mechanical Systems with Algebraic Constraints
- Data analysis tools for uncertainty quantification of inverse problems
- Data-consistent neural networks for solving nonlinear inverse problems
- Deblurring Images
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Deep neural networks motivated by partial differential equations
- For most large underdetermined systems of linear equations the minimal đ1ânorm solution is also the sparsest solution
- From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images
- Learning regularization functionals a supervised training approach
- Learning regularization parameters of inverse problems via deep neural networks
- Nonlinear inverse scale space methods
- Nonlinear total variation based noise removal algorithms
- Nonstationary iterated Tikhonov regularization
- Rank-Deficient and Discrete Ill-Posed Problems
- Solving ill-posed inverse problems using iterative deep neural networks
- Statistical regularization of inverse problems
- The mathematics of computerized tomography
- Unsupervised knowledge-transfer for learned image reconstruction
Cited in
(4)- Regularising inverse problems with generative machine learning models
- Short Communication: Localized Adversarial Artifacts for Compressed Sensing MRI
- Relaxation approach for learning neural network regularizers for a class of identification problems
- Inverse problems are solvable on real number signal processing hardware
This page was built for publication: DRIP: deep regularizers for inverse problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6141552)
