Marco Prato
YOU?
Author Swipe
View article: Computing <i>p</i> th root of a transition matrix with a deep unsupervised learning approach
Computing <i>p</i> th root of a transition matrix with a deep unsupervised learning approach Open
Transition matrices are a tool used to describe transition probabilities of a Markovian process. From an applied perspective, transition matrices are, for example, used in the fields of credit risk modeling and medical decision analysis. I…
View article: A hybrid interior point - deep learning approach for Poisson image deblurring
A hybrid interior point - deep learning approach for Poisson image deblurring Open
International audience
View article: A nested primal–dual iterated Tikhonov method for regularized convex optimization
A nested primal–dual iterated Tikhonov method for regularized convex optimization Open
Proximal–gradient methods are widely employed tools in imaging that can be accelerated by adopting variable metrics and/or extrapolation steps. One crucial issue is the inexact computation of the proximal operator, often implemented throug…
View article: Algorithmic unfolding for image reconstruction and localization problems in fluorescence microscopy
Algorithmic unfolding for image reconstruction and localization problems in fluorescence microscopy Open
We propose an unfolded accelerated projected-gradient descent procedure to estimate model and algorithmic parameters for image super-resolution and molecule localization problems in image microscopy. The variational lower-level constraint …
View article: A new proximal heavy ball inexact line-search algorithm
A new proximal heavy ball inexact line-search algorithm Open
We study a novel inertial proximal-gradient method for composite optimization. The proposed method alternates between a variable metric proximal-gradient iteration with momentum and an Armijo-like linesearch based on the sufficient decreas…
View article: Denoising Diffusion Models on Model-Based Latent Space
Denoising Diffusion Models on Model-Based Latent Space Open
With the recent advancements in the field of diffusion generative models, it has been shown that defining the generative process in the latent space of a powerful pretrained autoencoder can offer substantial advantages. This approach, by a…
View article: CTprintNet: An Accurate and Stable Deep Unfolding Approach for Few-View CT Reconstruction
CTprintNet: An Accurate and Stable Deep Unfolding Approach for Few-View CT Reconstruction Open
In this paper, we propose a new deep learning approach based on unfolded neural networks for the reconstruction of X-ray computed tomography images from few views. We start from a model-based approach in a compressed sensing framework, des…
View article: On an iteratively reweighted linesearch based algorithm for nonconvex composite optimization
On an iteratively reweighted linesearch based algorithm for nonconvex composite optimization Open
In this paper we propose a new algorithm for solving a class of nonsmooth nonconvex problems, which is obtained by combining the iteratively reweighted scheme with a finite number of forward–backward iterations based on a linesearch proced…
View article: Explainable bilevel optimization: An application to the Helsinki deblur challenge
Explainable bilevel optimization: An application to the Helsinki deblur challenge Open
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 recon…
View article: Biomedical Image Classification via Dynamically Early Stopped Artificial Neural Network
Biomedical Image Classification via Dynamically Early Stopped Artificial Neural Network Open
It is well known that biomedical imaging analysis plays a crucial role in the healthcare sector and produces a huge quantity of data. These data can be exploited to study diseases and their evolution in a deeper way or to predict their ons…
View article: Explainable bilevel optimization: an application to the Helsinki deblur challenge
Explainable bilevel optimization: an application to the Helsinki deblur challenge Open
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 recon…
View article: Deep Image Prior for medical image denoising, a study about parameter initialization
Deep Image Prior for medical image denoising, a study about parameter initialization Open
Convolutional Neural Networks are widely known and used architectures in image processing contexts, in particular for medical images. These Deep Learning techniques, known for their ability to extract high-level features, almost always req…
View article: Learning the Image Prior by Unrolling an Optimization Method
Learning the Image Prior by Unrolling an Optimization Method Open
Nowadays neural networks are omnipresent thanks to the amazing adaptability they possess, despite their poor interpretability and the difficulties they give when manipulating the parameters. On the other side, we have the classical variati…
View article: DCT-Former: Efficient Self-Attention with Discrete Cosine Transform
DCT-Former: Efficient Self-Attention with Discrete Cosine Transform Open
Since their introduction the Trasformer architectures emerged as the dominating architectures for both natural language processing and, more recently, computer vision applications. An intrinsic limitation of this family of "fully-attentive…
View article: Deep learning-assisted analysis of automobiles handling performances
Deep learning-assisted analysis of automobiles handling performances Open
The luxury car market has demanding product development standards aimed at providing state-of-the-art features in the automotive domain. Handling performance is amongst the most important properties that must be assessed when developing a …
View article: A comparison of nested primal-dual forward-backward methods for Poisson image deblurring
A comparison of nested primal-dual forward-backward methods for Poisson image deblurring Open
We consider an inexact version of the popular Fast Iterative Soft-Thresholding Algorithm (FISTA) suited for minimizing the sum of a differentiable convex data fidelity function plus a nondifferentiable convex regularizer whose proximal ope…
View article: Deep Neural Networks for Inverse Problems with Pseudodifferential Operators: An Application to Limited-Angle Tomography
Deep Neural Networks for Inverse Problems with Pseudodifferential Operators: An Application to Limited-Angle Tomography Open
We propose a novel convolutional neural network (CNN), called $Ψ$DONet, designed for learning pseudodifferential operators ($Ψ$DOs) in the context of linear inverse problems. Our starting point is the Iterative Soft Thresholding Algorithm …
View article: A Hybrid Interior Point - Deep Learning Approach for Poisson Image Deblurring
A Hybrid Interior Point - Deep Learning Approach for Poisson Image Deblurring Open
In this paper we address the problem of deconvolution of an image corrupted with Poisson noise by reformulating the restoration process as a constrained minimization of a suitable regularized data fidelity function. The minimization step i…
View article: Deep neural networks for inverse problems with pseudodifferential\n operators: an application to limited-angle tomography
Deep neural networks for inverse problems with pseudodifferential\n operators: an application to limited-angle tomography Open
We propose a novel convolutional neural network (CNN), called $\\Psi$DONet,\ndesigned for learning pseudodifferential operators ($\\Psi$DOs) in the context\nof linear inverse problems. Our starting point is the Iterative Soft\nThresholding…
View article: Convergence of Inexact Forward--Backward Algorithms Using the Forward--Backward Envelope
Convergence of Inexact Forward--Backward Algorithms Using the Forward--Backward Envelope Open
This paper deals with a general framework for inexact forward--backward algorithms aimed at minimizing the sum of an analytic function and a lower semicontinuous, subanalytic, convex term. Such a framework relies on an implementable inexac…
View article: Deep unfolding of a proximal interior point method for image restoration
Deep unfolding of a proximal interior point method for image restoration Open
Variational methods are widely applied to ill-posed inverse problems for they have the ability to embed prior knowledge about the solution. However, the level of performance of these methods significantly depends on a set of parameters, wh…
View article: Learned Image Deblurring by Unfolding a Proximal Interior Point Algorithm
Learned Image Deblurring by Unfolding a Proximal Interior Point Algorithm Open
International audience