Optimality Conditions for Bilevel Imaging Learning Problems with Total Variation Regularization
From MaRDI portal
Numerical optimization and variational techniques (65K10) Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies for image processing (68U10) Complementarity and equilibrium problems and variational inequalities (finite dimensions) (aspects of mathematical programming) (90C33) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)
Abstract: We address the problem of optimal scale-dependent parameter learning in total variation image denoising. Such problems are formulated as bilevel optimization instances with total variation denoising problems as lower-level constraints. For the bilevel problem, we are able to derive M-stationarity conditions, after characterizing the corresponding Mordukhovich generalized normal cone and verifying suitable constraint qualification conditions. We also derive B-stationarity conditions, after investigating the Lipschitz continuity and directional differentiability of the lower-level solution operator. A characterization of the Bouligand subdifferential of the solution mapping, by means of a properly defined linear system, is provided as well. Based on this characterization, we propose a two-phase non-smooth trust-region algorithm for the numerical solution of the bilevel problem and test it computationally for two particular experimental settings.
Recommendations
- A bilevel optimization approach for parameter learning in variational models
- Bilevel parameter learning for higher-order total variation regularisation models
- Bilevel approaches for learning of variational imaging models
- Learning optimal spatially-dependent regularization parameters in total variation image denoising
- Inexact derivative-free optimization for bilevel learning
Cites work
- A bilevel optimization approach for parameter learning in variational models
- A Generalized Mathematical Program with Equilibrium Constraints
- A nonsmooth trust-region method for locally Lipschitz functions with application to optimization problems constrained by variational inequalities
- Analysis and automatic parameter selection of a variational model for mixed Gaussian and salt-and-pepper noise removal
- Bilevel approaches for learning of variational imaging models
- Bilevel optimization for calibrating point spread functions in blind deconvolution
- Bilevel parameter learning for higher-order total variation regularisation models
- Bilevel parameter learning for nonlocal image denoising models
- Crouzeix-Raviart approximation of the total variation on simplicial meshes
- Dualization and Automatic Distributed Parameter Selection of Total Generalized Variation via Bilevel Optimization
- Dynamic sampling schemes for optimal noise learning under multiple nonsmooth constraints
- Generating structured nonsmooth priors and associated primal-dual methods
- scientific article; zbMATH DE number 1727434 (Why is no real title available?)
- scientific article; zbMATH DE number 3852340 (Why is no real title available?)
- scientific article; zbMATH DE number 686746 (Why is no real title available?)
- scientific article; zbMATH DE number 1376935 (Why is no real title available?)
- Image denoising: learning the noise model via nonsmooth PDE-constrained optimization
- Introduction to Piecewise Differentiable Equations
- Learning consistent discretizations of the total variation
- Learning optimal spatially-dependent regularization parameters in total variation image denoising
- Numerical PDE-constrained optimization
- Structural Properties of Solutions to Total Variation Regularization Problems
- Techniques for gradient-based bilevel optimization with non-smooth lower level problems
- The structure of optimal parameters for image restoration problems
- Variational Analysis
Cited in
(19)- Inexact derivative-free optimization for bilevel learning
- Bilevel optimization for calibrating point spread functions in blind deconvolution
- A bilevel optimization approach for parameter learning in variational models
- Dynamic sampling schemes for optimal noise learning under multiple nonsmooth constraints
- Prior Learning and Convex-Concave Regularization of Binary Tomography
- Bilevel approaches for learning of variational imaging models
- A bilevel approach for parameter learning in inverse problems
- Learning optimal spatially-dependent regularization parameters in total variation image denoising
- Bilevel Imaging Learning Problems as Mathematical Programs with Complementarity Constraints: Reformulation and Theory
- Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling
- Linearly convergent bilevel optimization with single-step inner methods
- Bilevel optimization methods in imaging
- Interpretable model learning in variational imaging: a bilevel optimization approach
- Bilevel parameter learning for higher-order total variation regularisation models
- Single-loop methods for bilevel parameter learning in inverse imaging
- Data-driven methods for quantitative imaging
- Dyadic partition-based training schemes for TV/TGV denoising
- Preconditioned Douglas-Rachford algorithms for TV- and TGV-regularized variational imaging problems
- The structure of optimal parameters for image restoration problems
This page was built for publication: Optimality Conditions for Bilevel Imaging Learning Problems with Total Variation Regularization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5056917)
