Livello precedente |
Pietro Cagnasso. Efficiency and Generalization in Federated Learning: Insights from Sharpness-Aware Minimization. Rel. Barbara Caputo, Debora Caldarola, Marco Ciccone. Politecnico di Torino, Corso di laurea magistrale in Data Science And Engineering, 2023
Luca Marcellino. Visual Transformers for Federated Learning: Exploring the Role of Architecture Layers in Generalization Enhancement. Rel. Barbara Caputo, Debora Caldarola, Marco Ciccone. Politecnico di Torino, Corso di laurea magistrale in Data Science And Engineering, 2023
Mattia Dutto. Federated Visual Geo-Localization. Rel. Barbara Caputo, Carlo Masone, Debora Caldarola, Eros Fani', Gabriele Moreno Berton. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering), 2023
Andrea Silvi. Sequential to Parallel Federated Learning with Semantic-Aware Client Groupings. Rel. Barbara Caputo, Debora Caldarola, Marco Ciccone. Politecnico di Torino, Corso di laurea magistrale in Data Science And Engineering, 2022
Andrea Rizzardi. Speeding up convergence while preserving privacy in Heterogeneous Federated Learning. Rel. Barbara Caputo, Debora Caldarola, Marco Ciccone. Politecnico di Torino, Corso di laurea magistrale in Data Science And Engineering, 2022
Eros Fani'. On the Challenges of Class Imbalance in Federated Learning for Semantic Segmentation. Rel. Barbara Caputo, Debora Caldarola, Fabio Cermelli, Antonio Tavera. Politecnico di Torino, Corso di laurea magistrale in Data Science And Engineering, 2021
Lidia Fantauzzo. On the Challenges of Federated Learning in Semantic Segmentation across Domains. Rel. Barbara Caputo, Debora Caldarola, Fabio Cermelli, Antonio Tavera. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Matematica, 2021