Zobrazeno 1 - 10
of 12 780
pro vyhledávání: '"Luzi, A."'
Image classification models, including convolutional neural networks (CNNs), perform well on a variety of classification tasks but struggle under conditions of partial occlusion, i.e., conditions in which objects are partially covered from the view o
Externí odkaz:
http://arxiv.org/abs/2409.10775
Generative models unfairly penalize data belonging to minority classes, suffer from model autophagy disorder (MADness), and learn biased estimates of the underlying distribution parameters. Our theoretical and empirical results show that training gen
Externí odkaz:
http://arxiv.org/abs/2405.13977
The rapid advancement of Generative Adversarial Networks (GANs) necessitates the need to robustly evaluate these models. Among the established evaluation criteria, the Fr\'{e}chetInception Distance (FID) has been widely adopted due to its conceptual
Externí odkaz:
http://arxiv.org/abs/2310.20636
Publikováno v:
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XLVIII-3-2024, Pp 319-324 (2024)
InSAR often demands the installation of artificial reflectors, usually represented by Passive Corner Reflectors (PCR). This occurs when in the imaged areas the coherence is low, and the density of Persistent Scatterers (PS) is scarce or even non-exis
Externí odkaz:
https://doaj.org/article/6c4187425ee64291ab962a61e36e8348
Autor:
O. Monserrat, A. Barra, M. Béjar-Pizarro, J. S. Rivera, J. P. Galve, C. Guardiola, M. Cuevas-González, R. M. Mateos, P. Ezquerro, J. M. Azañon, S. Shahbazi, J. Navarro, M. Crosetto, G. Luzi
Publikováno v:
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XLVIII-3-2024, Pp 351-356 (2024)
The availability of displacement maps based on Multi-Temporal Satellite SAR Interferometry (MT-InSAR) has greatly increased, particularly since the launch of the Copernicus Sentinel-1 satellites in 2014. These satellites provide open and free data, l
Externí odkaz:
https://doaj.org/article/b8881efc2c5a401695f33bc3d7a4ca2b
Publikováno v:
Earth System Science Data, Vol 16, Pp 4843-4867 (2024)
In this paper, the new dynamic geophysical and geochemical MUltiparametric DAtabase (MUDA) is presented. MUDA is a new infrastructure of the National Institute of Geophysics and Volcanology (INGV), published online in December 2023, with the aim of a
Externí odkaz:
https://doaj.org/article/f3f4039a836a4af1bdc1fb8f9582f893
Autor:
Loredana Mulas, Elena Santini, Marta Azzolin, Mauro Buonocore, Ilaria Campana, Lara Carosso, Giovanni Coppini, Matteo Costantino, Léa David, Marianna Farina, Livio Favaro, Natalia Fraija-Fernández, Marco Gamba, Maria Leonor Garcia Gutiérrez, Cristina Giacoma, Martina Gregorietti, Rita Lecci, Giulia Luzi, Fulvio Maffucci, Francesco Paolo Mancuso, Valeria Masala, Erica Moura, Eugenia Pasanisi, Juan Antonio Raga, Selvaggia Santin, Gianluca Sarà, Antonella Servidio, Paola Tepsich, Francesco Tomasinelli, Gianluca Treglia, Roberta Teti, Elena Valsecchi, Morgana Vighi, Antonella Arcangeli
Publikováno v:
ARPHA Proceedings, Vol 6, Iss , Pp 79-82 (2024)
The manuscript provides an overview of the mid-term results of the citizen science campaign activities conducted within the Life CONCEPTU MARIS project (LIFE20 NAT/IT/001371) whose aim is to improve the conservation status of cetaceans and pelagic se
Externí odkaz:
https://doaj.org/article/7c431af246584a428e3a8eede52379eb
Autor:
Alemohammad, Sina, Casco-Rodriguez, Josue, Luzi, Lorenzo, Humayun, Ahmed Imtiaz, Babaei, Hossein, LeJeune, Daniel, Siahkoohi, Ali, Baraniuk, Richard G.
Seismic advances in generative AI algorithms for imagery, text, and other data types has led to the temptation to use synthetic data to train next-generation models. Repeating this process creates an autophagous (self-consuming) loop whose properties
Externí odkaz:
http://arxiv.org/abs/2307.01850
Autor:
Ren, Simiao, Luzi, Francesco, Lahrichi, Saad, Kassaw, Kaleb, Collins, Leslie M., Bradbury, Kyle, Malof, Jordan M.
Recently, the first foundation model developed specifically for image segmentation tasks was developed, termed the "Segment Anything Model" (SAM). SAM can segment objects in input imagery based on cheap input prompts, such as one (or more) points, a
Externí odkaz:
http://arxiv.org/abs/2304.13000
Publikováno v:
BMC Health Services Research, Vol 24, Iss 1, Pp 1-16 (2024)
Abstract Background An equal distribution of hospital structures represents an important factor to achieve Universal Health Coverage. Generally, the most diffused approach to measure the potential availability to healthcare is the provider-to-populat
Externí odkaz:
https://doaj.org/article/08fea6a1ec0747a2bdd5c7de20dce09d