Explainable bilevel optimization: an application to the Helsinki Deblur Challenge
From MaRDI portal
Publication:6169501
Abstract: In this paper we present a bilevel optimization scheme for the solution of a general image deblurring problem, in which a parametric variational-like approach is encapsulated within a machine learning scheme to provide a high quality reconstructed image with automatically learned parameters. The ingredients of the variational lower level and the machine learning upper one are specifically chosen for the Helsinki Deblur Challenge 2021, in which sequences of letters are asked to be recovered from out-of-focus photographs with increasing levels of blur. Our proposed procedure for the reconstructed image consists in a fixed number of FISTA iterations applied to the minimization of an edge preserving and binarization enforcing regularized least-squares functional. The parameters defining the variational model and the optimization steps, which, unlike most deep learning approaches, all have a precise and interpretable meaning, are learned via either a similarity index or a support vector machine strategy. Numerical experiments on the test images provided by the challenge authors show significant gains with respect to a standard variational approach and performances comparable with those of some of the proposed deep learning based algorithms which require the optimization of millions of parameters.
Recommendations
- A bilevel optimization approach for parameter learning in variational models
- 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
- Inexact derivative-free optimization for bilevel learning
Cites work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- A bilevel optimization approach for parameter learning in variational models
- A scaled gradient projection method for constrained image deblurring
- Adaptive FISTA for Nonconvex Optimization
- Bilevel optimization with nonsmooth lower level problems
- Computed tomography with view angle estimation using uncertainty quantification
- Deep unfolding of a proximal interior point method for image restoration
- Efficient gradient projection methods for edge-preserving removal of Poisson noise
- Fields of experts
- Inertial variable metric techniques for the inexact forward-backward algorithm
- Insights Into Analysis Operator Learning: From Patch-Based Sparse Models to Higher Order MRFs
- Neural architecture search via standard machine learning methodologies
- New convergence results for the scaled gradient projection method
- On the convergence of the iterates of the ``fast iterative shrinkage/thresholding algorithm
- Projected subgradient methods with non-Euclidean distances for non-differentiable convex minimization and variational inequalities
- Ritz-like values in steplength selections for stochastic gradient methods
- Smooth minimization of non-smooth functions
- Solving inverse problems using data-driven models
- The Little Engine that Could: Regularization by Denoising (RED)
- Variational networks: an optimal control approach to early stopping variational methods for image restoration
Cited in
(3)
This page was built for publication: Explainable bilevel optimization: an application to the Helsinki Deblur Challenge
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6169501)
