1 code implementation • EURO Journal on Computational Optimization 2024 • Pasquale Cascarano, Giorgia Franchini, Erich Kobler, Federica Porta, Andrea Sebastiani
To control the variance of the objective's gradients, we use an automatic sample size selection along with a variable metric to precondition the stochastic gradient directions.
no code implementations • 31 Aug 2023 • Alessandro Benfenati, Emilie Chouzenoux, Giorgia Franchini, Salla Latva-Aijo, Dominik Narnhofer, Jean-Christophe Pesquet, Sebastian J. Scott, Mahsa Yousefi
Several decades ago, Support Vector Machines (SVMs) were introduced for performing binary classification tasks, under a supervised framework.
1 code implementation • 17 Apr 2023 • Elena Govi, Davide Sapienza, Carmelo Scribano, Tobia Poppi, Giorgia Franchini, Paola Ardòn, Micaela Verucchi, Marko Bertogna
We analyze how the presence of the markers affects the pose estimation accuracy, and how this bias may be mitigated through data augmentation and other methods.
no code implementations • 18 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.
1 code implementation • 3 Oct 2022 • Carmelo Scribano, Giorgia Franchini, Ignacio Sañudo Olmedo, Marko Bertogna
Perceiving the surrounding environment is essential for enabling autonomous or assisted driving functionalities.
1 code implementation • Computational Optimization and Applications 2022 • Pasquale Cascarano, Giorgia Franchini, Erich Kobler, Federica Porta, Andrea Sebastiani
Numerical results demonstrate the robustness with respect to image content, noise levels and hyperparameters of the proposed models on both denoising and deblurring of simulated as well as real natural and medical images.
1 code implementation • 2 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.
1 code implementation • 18 Jun 2021 • Carmelo Scribano, Davide Sapienza, Giorgia Franchini, Micaela Verucchi, Marko Bertogna
Combining Natural Language with Vision represents a unique and interesting challenge in the domain of Artificial Intelligence.
1 code implementation • 23 Sep 2020 • Pasquale Cascarano, Andrea Sebastiani, Maria Colomba Comes, Giorgia Franchini, Federica Porta
In the last decades, unsupervised deep learning based methods have caught researchers attention, since in many real applications, such as medical imaging, collecting a great amount of training examples is not always feasible.
no code implementations • 28 Jun 2019 • Giorgia Franchini, Mathilde Galinier, Micaela Verucchi
This approach can be of particular interest when the space of the characteristics of the network is notably large or when its full training is highly time-consuming.