no code implementations • 3 Mar 2024 • Roberto Di Via, Matteo Santacesaria, Francesca Odone, Vito Paolo Pastore
Our findings can provide an indication for the development of robust landmark detection systems in medical images when no large annotated dataset is available.
no code implementations • 29 Jan 2024 • Giovanni S. Alberti, Luca Ratti, Matteo Santacesaria, Silvia Sciutto
In inverse problems, it is widely recognized that the incorporation of a sparsity prior yields a regularization effect on the solution.
1 code implementation • 27 Mar 2023 • Giovanni S. Alberti, Johannes Hertrich, Matteo Santacesaria, Silvia Sciutto
Representing a manifold of very high-dimensional data with generative models has been shown to be computationally efficient in practice.
1 code implementation • 29 May 2022 • Giovanni S. Alberti, Matteo Santacesaria, Silvia Sciutto
In this work, we present and study Continuous Generative Neural Networks (CGNNs), namely, generative models in the continuous setting: the output of a CGNN belongs to an infinite-dimensional function space.
no code implementations • 29 Oct 2021 • Gianandrea Lanzara, Matteo Santacesaria
This paper proposes a spatial model with a realistic geography where a continuous distribution of agents (e. g., farmers) engages in economic interactions with one location from a finite set (e. g., cities).
1 code implementation • NeurIPS 2021 • Giovanni S. Alberti, Ernesto de Vito, Matti Lassas, Luca Ratti, Matteo Santacesaria
Then, we consider the problem of learning the regularizer from a finite training set in two different frameworks: one supervised, based on samples of both $x$ and $y$, and one unsupervised, based only on samples of $x$.
no code implementations • 5 Nov 2020 • Valentina Candiani, Matteo Santacesaria
We employ two neural network architectures -- a fully connected and a convolutional one -- for the classification of hemorrhagic and ischemic strokes.