24 citations · 73 across the 15 of their papers we have counts for
16 papers
A Relaxed Gradient Step Denoiser for Splitting Methods in Poisson Inverse Problems
Alessandro Benfenati
Plug and Play methods combine classical variational models with learned denoisers and have achieved strong results in imaging inverse problems. Their convergence has been widely st…
Plug and Play Splitting Techniques for Poisson Image Restoration
Alessandro Benfenati
Plug and Play (PnP) methods achieve remarkable results in the framework of image restoration problems for Gaussian data. Nonetheless, the theory available for the Gaussian case can…
RELD: Regularization by Latent Diffusion Models for Image Restoration
Pasquale Cascarano, Lorenzo Stacchio, Andrea Sebastiani +3
In recent years, Diffusion Models have become the new state-of-the-art in deep generative modeling, ending the long-time dominance of Generative Adversarial Networks. Inspired by t…
Unveiling Transformer Perception by Exploring Input Manifolds
Alessandro Benfenati, Alfio Ferrara, Alessio Marta +2
This paper introduces a general method for the exploration of equivalence classes in the input space of Transformer models. The proposed approach is based on sound mathematical the…
A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on -dimensional Classes
Alessandro Benfenati, Alessio Marta
Neural networks are playing a crucial role in everyday life, with the most modern generative models able to achieve impressive results. Nonetheless, their functioning is still not…
A Modular Deep Learning-based Approach for Diffuse Optical Tomography Reconstruction
Alessandro Benfenati, Paola Causin, Martina Quinteri
Medical imaging is nowadays a pillar in diagnostics and therapeutic follow-up. Current research tries to integrate established - but ionizing - tomographic techniques with technolo…
Constrained Regularization by Denoising with Automatic Parameter Selection
Pasquale Cascarano, Alessandro Benfenati, Ulugbek S. Kamilov +1
Regularization by Denoising (RED) is a well-known method for solving image restoration problems by using learned image denoisers as priors. Since the regularization parameter in th…
Majorization-Minimization for sparse SVMs
Alessandro Benfenati, Emilie Chouzenoux, Giorgia Franchini +5
Several decades ago, Support Vector Machines (SVMs) were introduced for performing binary classification tasks, under a supervised framework. Nowadays, they often outperform other…
A singular Riemannian geometry approach to Deep Neural Networks I. Theoretical foundations
Alessandro Benfenati, Alessio Marta
Deep Neural Networks are widely used for solving complex problems in several scientific areas, such as speech recognition, machine translation, image analysis. The strategies emplo…
Unsupervised deep learning techniques for powdery mildew recognition based on multispectral imaging
Alessandro Benfenati, Paola Causin, Roberto Oberti +1
Objectives. Sustainable management of plant diseases is an open challenge which has relevant economic and environmental impact. Optimal strategies rely on human expertise for field…
A singular Riemannian geometry approach to Deep Neural Networks II. Reconstruction of 1-D equivalence classes
Alessandro Benfenati, Alessio Marta
In a previous work, we proposed a geometric framework to study a deep neural network, seen as sequence of maps between manifolds, employing singular Riemannian geometry. In this pa…
A Deep Learning Generative Model Approach for Image Synthesis of Plant Leaves
Alessandro Benfenati, Davide Bolzi, Paola Causin +1
Objectives. We generate via advanced Deep Learning (DL) techniques artificial leaf images in an automatized way. We aim to dispose of a source of training samples for AI applicatio…
A Learned-SVD approach for Regularization in Diffuse Optical Tomography
Alessandro Benfenati, Giuseppe Bisazza, Paola Causin
Diffuse Optical Tomography (DOT) is an emerging technology in medical imaging which employs light in the NIR spectrum to estimate the distribution of optical coefficients in biolog…
Binary interaction methods for high dimensional global optimization and machine learning
Alessandro Benfenati, Giacomo Borghi, Lorenzo Pareschi
In this work we introduce a new class of gradient-free global optimization methods based on a binary interaction dynamics governed by a Boltzmann type equation. In each interaction…
A Proximal Approach for a Class of Matrix Optimization Problems
A. Benfenati, E. Chouzenoux, J. -C. Pesquet
In recent years, there has been a growing interest in mathematical models leading to the minimization, in a symmetric matrix space, of a Bregman divergence coupled with a regulariz…
Scaling techniques for -subgradient projection methods
Silvia Bonettini, Alessandro Benfenati, Valeria Ruggiero
The recent literature on first order methods for smooth optimization shows that significant improvements on the practical convergence behaviour can be achieved with variable stepsi…