Zobrazeno 1 - 10
of 821
pro vyhledávání: '"Amerini A"'
Adaptive gradient methods have been increasingly adopted by deep learning community due to their fast convergence and reduced sensitivity to hyper-parameters. However, these methods come with limitations, such as increased memory requirements for ele
Externí odkaz:
http://arxiv.org/abs/2411.15795
Autor:
Alfarano, Andrea, Alfarano, Alberto, Friso, Linda, Bacciu, Andrea, Amerini, Irene, Silvestri, Fabrizio
Spatio-Temporal predictive Learning is a self-supervised learning paradigm that enables models to identify spatial and temporal patterns by predicting future frames based on past frames. Traditional methods, which use recurrent neural networks to cap
Externí odkaz:
http://arxiv.org/abs/2411.10198
Quantum computing has introduced novel perspectives for tackling and improving machine learning tasks. Moreover, the integration of quantum technologies together with well-known deep learning (DL) architectures has emerged as a potential research tre
Externí odkaz:
http://arxiv.org/abs/2410.08677
Autor:
Amerini, Irene, Barni, Mauro, Battiato, Sebastiano, Bestagini, Paolo, Boato, Giulia, Bonaventura, Tania Sari, Bruni, Vittoria, Caldelli, Roberto, De Natale, Francesco, De Nicola, Rocco, Guarnera, Luca, Mandelli, Sara, Marcialis, Gian Luca, Micheletto, Marco, Montibeller, Andrea, Orru', Giulia, Ortis, Alessandro, Perazzo, Pericle, Puglisi, Giovanni, Salvi, Davide, Tubaro, Stefano, Tonti, Claudia Melis, Villari, Massimo, Vitulano, Domenico
AI-generated synthetic media, also called Deepfakes, have significantly influenced so many domains, from entertainment to cybersecurity. Generative Adversarial Networks (GANs) and Diffusion Models (DMs) are the main frameworks used to create Deepfake
Externí odkaz:
http://arxiv.org/abs/2408.00388
Publikováno v:
Computer Vision and Image Understanding 2024
Generative techniques continue to evolve at an impressively high rate, driven by the hype about these technologies. This rapid advancement severely limits the application of deepfake detectors, which, despite numerous efforts by the scientific commun
Externí odkaz:
http://arxiv.org/abs/2406.08171
The paper aims to investigate relevant computational issues of deep neural network architectures with an eye to the interaction between the optimization algorithm and the classification performance. In particular, we aim to analyze the behaviour of s
Externí odkaz:
http://arxiv.org/abs/2405.02089
Diffusion models (DMs) have revolutionized image generation, producing high-quality images with applications spanning various fields. However, their ability to create hyper-realistic images poses significant challenges in distinguishing between real
Externí odkaz:
http://arxiv.org/abs/2404.12908
Nowadays the accurate geo-localization of ground-view images has an important role across domains as diverse as journalism, forensics analysis, transports, and Earth Observation. This work addresses the problem of matching a query ground-view image w
Externí odkaz:
http://arxiv.org/abs/2404.11302
Data from satellites or aerial vehicles are most of the times unlabelled. Annotating such data accurately is difficult, requires expertise, and is costly in terms of time. Even if Earth Observation (EO) data were correctly labelled, labels might chan
Externí odkaz:
http://arxiv.org/abs/2404.11299
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology, 2023
Depth estimation is a fundamental knowledge for autonomous systems that need to assess their own state and perceive the surrounding environment. Deep learning algorithms for depth estimation have gained significant interest in recent years, owing to
Externí odkaz:
http://arxiv.org/abs/2403.08368