Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Caldarola, Debora"'
Autor:
Dutto, Mattia, Berton, Gabriele, Caldarola, Debora, Fanì, Eros, Trivigno, Gabriele, Masone, Carlo
Visual Place Recognition (VPR) aims to estimate the location of an image by treating it as a retrieval problem. VPR uses a database of geo-tagged images and leverages deep neural networks to extract a global representation, called descriptor, from ea
Externí odkaz:
http://arxiv.org/abs/2404.13324
Federated Learning (FL) aims to learn a global model from distributed users while protecting their privacy. However, when data are distributed heterogeneously the learning process becomes noisy, unstable, and biased towards the last seen clients' dat
Externí odkaz:
http://arxiv.org/abs/2310.01366
Autor:
Shenaj, Donald, Fanì, Eros, Toldo, Marco, Caldarola, Debora, Tavera, Antonio, Michieli, Umberto, Ciccone, Marco, Zanuttigh, Pietro, Caputo, Barbara
Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the collected data. However, most of the existing works on FL unrealisticall
Externí odkaz:
http://arxiv.org/abs/2210.02326
Models trained in federated settings often suffer from degraded performances and fail at generalizing, especially when facing heterogeneous scenarios. In this work, we investigate such behavior through the lens of geometry of the loss and Hessian eig
Externí odkaz:
http://arxiv.org/abs/2203.11834
Autor:
Fantauzzo, Lidia, Fanì, Eros, Caldarola, Debora, Tavera, Antonio, Cermelli, Fabio, Ciccone, Marco, Caputo, Barbara
Semantic Segmentation is essential to make self-driving vehicles autonomous, enabling them to understand their surroundings by assigning individual pixels to known categories. However, it operates on sensible data collected from the users' cars; thus
Externí odkaz:
http://arxiv.org/abs/2202.13670
Publikováno v:
26th International Conference on Pattern Recognition (ICPR), 2022, pp. 3376-3382
Federated Learning (FL) allows training machine learning models in privacy-constrained scenarios by enabling the cooperation of edge devices without requiring local data sharing. This approach raises several challenges due to the different statistica
Externí odkaz:
http://arxiv.org/abs/2201.10899
Autor:
Caldarola, Debora, Mancini, Massimiliano, Galasso, Fabio, Ciccone, Marco, Rodolà, Emanuele, Caputo, Barbara
Federated Learning (FL) deals with learning a central model (i.e. the server) in privacy-constrained scenarios, where data are stored on multiple devices (i.e. the clients). The central model has no direct access to the data, but only to the updates
Externí odkaz:
http://arxiv.org/abs/2104.14628
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.