Zobrazeno 1 - 10
of 2 534
pro vyhledávání: '"A, Camoriano"'
Federated Learning (FL) methods often struggle in highly statistically heterogeneous settings. Indeed, non-IID data distributions cause client drift and biased local solutions, particularly pronounced in the final classification layer, negatively imp
Externí odkaz:
http://arxiv.org/abs/2406.01116
Autor:
Maracani, Andrea, Camoriano, Raffaello, Maiettini, Elisa, Talon, Davide, Rosasco, Lorenzo, Natale, Lorenzo
This study provides a comprehensive benchmark framework for Source-Free Unsupervised Domain Adaptation (SF-UDA) in image classification, aiming to achieve a rigorous empirical understanding of the complex relationships between multiple key design fac
Externí odkaz:
http://arxiv.org/abs/2402.16090
Autor:
Duan, Anqing, Liuchen, Wanli, Wu, Jinsong, Camoriano, Raffaello, Rosasco, Lorenzo, Navarro-Alarcon, David
The increasing deployment of robots has significantly enhanced the automation levels across a wide and diverse range of industries. This paper investigates the automation challenges of laser-based dermatology procedures in the beauty industry; This g
Externí odkaz:
http://arxiv.org/abs/2312.13623
Autor:
Duan, Anqing, Batzianoulis, Iason, Camoriano, Raffaello, Rosasco, Lorenzo, Pucci, Daniele, Billard, Aude
We propose a structured prediction approach for robot imitation learning from demonstrations. Among various tools for robot imitation learning, supervised learning has been observed to have a prominent role. Structured prediction is a form of supervi
Externí odkaz:
http://arxiv.org/abs/2309.14829
High Power Laser's (HPL) optimal performance is essential for the success of a wide variety of experimental tasks related to light-matter interactions. Traditionally, HPL parameters are optimised in an automated fashion relying on black-box numerical
Externí odkaz:
http://arxiv.org/abs/2304.12187
Autor:
Maracani, Andrea, Camoriano, Raffaello, Maiettini, Elisa, Talon, Davide, Rosasco, Lorenzo, Natale, Lorenzo
Fine-tuning and Domain Adaptation emerged as effective strategies for efficiently transferring deep learning models to new target tasks. However, target domain labels are not accessible in many real-world scenarios. This led to the development of Uns
Externí odkaz:
http://arxiv.org/abs/2302.05379
Popular industrial robotic problems such as spray painting and welding require (i) conditioning on free-shape 3D objects and (ii) planning of multiple trajectories to solve the task. Yet, existing solutions make strong assumptions on the form of inpu
Externí odkaz:
http://arxiv.org/abs/2211.06930
Autor:
Ellen Meltzer, Laurie Wilshusen, Isra Abdulwadood, Claire Yee, Amy Sherman, Kelli Strader, Barbara Thomley, Denise Millstine, Jon Tilburt, Heather Fields, Larry Bergstrom, David Patchett, John Camoriano, Brent Bauer
Publikováno v:
JMIR Formative Research, Vol 8, p e56312 (2024)
BackgroundThe use of telemedicine (TELE) increased exponentially during the COVID-19 pandemic. While patient experience with TELE has been studied in other medical disciplines, its impact and applicability to integrative medicine practices remain unk
Externí odkaz:
https://doaj.org/article/68e2ca07faa94d0bbe5693de9ea8d55e
Publikováno v:
Il Foro Italiano, 1932 Jan 01. 57, 597/598-599/600.
Externí odkaz:
https://www.jstor.org/stable/23128232
Autor:
Ferigo, Diego, Camoriano, Raffaello, Viceconte, Paolo Maria, Calandriello, Daniele, Traversaro, Silvio, Rosasco, Lorenzo, Pucci, Daniele
Publikováno v:
IEEE Robotics and Automation Letters (RA-L) 2021
Balancing and push-recovery are essential capabilities enabling humanoid robots to solve complex locomotion tasks. In this context, classical control systems tend to be based on simplified physical models and hard-coded strategies. Although successfu
Externí odkaz:
http://arxiv.org/abs/2104.14534