Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Talon, Davide"'
Vision-Language Models (VLMs) have shown significant promise in Visual Question Answering (VQA) tasks by leveraging web-scale multimodal datasets. However, these models often struggle with continual learning due to catastrophic forgetting when adapti
Externí odkaz:
http://arxiv.org/abs/2411.02210
Autor:
Litrico, Mattia, Talon, Davide, Battiato, Sebastiano, Del Bue, Alessio, Giuffrida, Mario Valerio, Morerio, Pietro
Standard Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target but usually requires simultaneous access to both source and target data. Moreover, UDA approaches commonly assume that source
Externí odkaz:
http://arxiv.org/abs/2404.10574
Causal Representation Learning (CRL) aims at identifying high-level causal factors and their relationships from high-dimensional observations, e.g., images. While most CRL works focus on learning causal representations in a single environment, in thi
Externí odkaz:
http://arxiv.org/abs/2403.09830
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:
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
Puzzle solving is a combinatorial challenge due to the difficulty of matching adjacent pieces. Instead, we infer a mental image from all pieces, which a given piece can then be matched against avoiding the combinatorial explosion. Exploiting advancem
Externí odkaz:
http://arxiv.org/abs/2207.05634
Publikováno v:
In Pattern Recognition Letters January 2025 187:35-41
