Zobrazeno 1 - 10
of 3 298
pro vyhledávání: '"P. Aversa"'
We propose an unsupervised image segmentation method using features from pre-trained text-to-image diffusion models. Inspired by classic spectral clustering approaches, we construct adjacency matrices from self-attention layers between image patches
Externí odkaz:
http://arxiv.org/abs/2412.04678
Accurately detecting and classifying damage in analogue media such as paintings, photographs, textiles, mosaics, and frescoes is essential for cultural heritage preservation. While machine learning models excel in correcting degradation if the damage
Externí odkaz:
http://arxiv.org/abs/2412.04580
Autor:
A. Montanaro, W. Wei, D. De Fazio, U. Sassi, G. Soavi, P. Aversa, A. C. Ferrari, H. Happy, P. Legagneux, E. Pallecchi
Publikováno v:
Nature Communications, Vol 12, Iss 1, Pp 1-10 (2021)
Here, the authors report optoelectronic mixing up to 67 GHz using high-frequency back-gated graphene field effect transistors (GFETs). These devices mix an electrical signal injected into the GFET gate and a modulated optical signal onto a single lay
Externí odkaz:
https://doaj.org/article/79c0c0d231324053a7d93d22cb71996d
Publikováno v:
European Conference on Computer Vision (ECCV) Workshop on VISART, 2024
Accurately detecting and classifying damage in analogue media such as paintings, photographs, textiles, mosaics, and frescoes is essential for cultural heritage preservation. While machine learning models excel in correcting global degradation if the
Externí odkaz:
http://arxiv.org/abs/2408.12953
Autor:
Tragakis, Athanasios, Aversa, Marco, Kaul, Chaitanya, Murray-Smith, Roderick, Faccio, Daniele
In this work, we introduce Pixelsmith, a zero-shot text-to-image generative framework to sample images at higher resolutions with a single GPU. We are the first to show that it is possible to scale the output of a pre-trained diffusion model by a fac
Externí odkaz:
http://arxiv.org/abs/2406.07251
Autor:
A. Montanaro, W. Wei, D. De Fazio, U. Sassi, G. Soavi, P. Aversa, A. C. Ferrari, H. Happy, P. Legagneux, E. Pallecchi
Publikováno v:
Nature Communications, Vol 12, Iss 1, Pp 1-1 (2021)
Externí odkaz:
https://doaj.org/article/324e47ba28c84f68abb1dd649b81d185
Autor:
Nobis, Gabriel, Springenberg, Maximilian, Aversa, Marco, Detzel, Michael, Daems, Rembert, Murray-Smith, Roderick, Nakajima, Shinichi, Lapuschkin, Sebastian, Ermon, Stefano, Birdal, Tolga, Opper, Manfred, Knochenhauer, Christoph, Oala, Luis, Samek, Wojciech
We introduce the first continuous-time score-based generative model that leverages fractional diffusion processes for its underlying dynamics. Although diffusion models have excelled at capturing data distributions, they still suffer from various lim
Externí odkaz:
http://arxiv.org/abs/2310.17638
Autor:
Marta Garcia de Herreros, Natalia Jiménez, Leonardo Rodríguez-Carunchio, Eva Lillo, Mercedes Marín-Aguilera, Laura Ferrer-Mileo, Caterina Aversa, Samuel García-Esteve, Joan Padrosa, Isabel Trias, Laia Fernández-Mañas, Albert Font, Isabel Chirivella, Mariona Figols, Miguel Ángel Climent, Aleix Prat, Òscar Reig, Begoña Mellado
Publikováno v:
European Urology Open Science, Vol 70, Iss , Pp 86-90 (2024)
Alterations in the tumor suppressor genes (TSGs) RB1, PTEN, and TP53 are associated with treatment resistance, worse survival, and aggressive variants of prostate cancer (AVPC). We previously developed and validated a signature reflecting low TSG exp
Externí odkaz:
https://doaj.org/article/bbfdf6631a7e44cc9c6c254191b07fed
Publikováno v:
Italian Journal of Pediatrics, Vol 50, Iss 1, Pp 1-5 (2024)
Abstract Filters and photoediting are widely used to transform or alter photos, mainly selfies, before sharing with friends or on social networks. In adult population there is a strong evidence of the potential risks of this behaviuor. Aim of the pre
Externí odkaz:
https://doaj.org/article/bdc0d0940386441996224aa7debf8bd2
Publikováno v:
Mater. Today Commun. 35 (2023) 105532
This paper introduces a new ontology for Materials Science Laboratory Equipment, termed MSLE. A fundamental issue with materials science laboratory (hereafter lab) equipment in the real world is that scientists work with various types of equipment wi
Externí odkaz:
http://arxiv.org/abs/2308.07325