Search Results for author: Marco Prato

Found 5 papers, 3 papers with code

Explainable bilevel optimization: an application to the Helsinki deblur challenge

no code implementations18 Oct 2022 Silvia Bonettini, Giorgia Franchini, Danilo Pezzi, Marco Prato

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.

Bilevel Optimization Binarization +2

DCT-Former: Efficient Self-Attention with Discrete Cosine Transform

1 code implementation2 Mar 2022 Carmelo Scribano, Giorgia Franchini, Marco Prato, Marko Bertogna

Since their introduction the Trasformer architectures emerged as the dominating architectures for both natural language processing and, more recently, computer vision applications.

Data Compression

Deep neural networks for inverse problems with pseudodifferential operators: an application to limited-angle tomography

1 code implementation2 Jun 2020 Tatiana A. Bubba, Mathilde Galinier, Matti Lassas, Marco Prato, Luca Ratti, Samuli Siltanen

We propose a novel convolutional neural network (CNN), called $\Psi$DONet, designed for learning pseudodifferential operators ($\Psi$DOs) in the context of linear inverse problems.

Deep Unfolding of a Proximal Interior Point Method for Image Restoration

1 code implementation11 Dec 2018 Carla Bertocchi, Emilie Chouzenoux, Marie-Caroline Corbineau, Jean-Christophe Pesquet, Marco Prato

Variational methods are widely applied to ill-posed inverse problems for they have the ability to embed prior knowledge about the solution.

Deblurring Image Deblurring +1

A scaled gradient projection method for Bayesian learning in dynamical systems

no code implementations25 Jun 2014 Silvia Bonettini, Alessandro Chiuso, Marco Prato

If the unknown impulse response is modeled as a Gaussian process with a suitable kernel, the maximization of the marginal likelihood leads to a challenging nonconvex optimization problem, which requires a stable and effective solution strategy.

Second-order methods Test

Cannot find the paper you are looking for? You can Submit a new open access paper.