71 citations · 82 across the 6 of their papers we have counts for
6 papers
Neural Learning of Fast Matrix Multiplication Algorithms: A StrassenNet Approach
Paolo Andreini, Alessandra Bernardi, Monica Bianchini +4
Fast matrix multiplication can be described as searching for low-rank decompositions of the matrix--multiplication tensor. We design a neural architecture, \textsc{StrassenNet}, wh…
Who Made This? Fake Detection and Source Attribution with Diffusion Features
Simone Bonechi, Paolo Andreini, Barbara Toniella Corradini
The rapid rise of generative models has yielded synthetic images of striking realism, blurring the line between real and fake content. As novel models proliferate, detectors must g…
A multi-stage GAN for multi-organ chest X-ray image generation and segmentation
Giorgio Ciano, Paolo Andreini, Tommaso Mazzierli +2
Multi-organ segmentation of X-ray images is of fundamental importance for computer aided diagnosis systems. However, the most advanced semantic segmentation methods rely on deep le…
Deep Dynamic Factor Models
Paolo Andreini, Cosimo Izzo, Giovanni Ricco
A novel deep neural network framework -- that we refer to as Deep Dynamic Factor Model (DFM) --, is able to encode the information available, from hundreds of macroeconomic and…
Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation
Simone Bonechi, Paolo Andreini, Monica Bianchini +1
Providing pixel-level supervisions for scene text segmentation is inherently difficult and costly, so that only few small datasets are available for this task. To face the scarcity…
A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation
Paolo Andreini, Simone Bonechi, Monica Bianchini +3
In recent years, the use of deep learning is becoming increasingly popular in computer vision. However, the effective training of deep architectures usually relies on huge sets of…