Zobrazeno 1 - 10
of 3 279
pro vyhledávání: '"Lombaert"'
Foundation models such as the recently introduced Segment Anything Model (SAM) have achieved remarkable results in image segmentation tasks. However, these models typically require user interaction through handcrafted prompts such as bounding boxes,
Externí odkaz:
http://arxiv.org/abs/2409.20293
Autor:
Mallez, Sophie, Castagnone, Chantal, Lombaert, Eric, Castagnone-Sereno, Philippe, Guillemaud, Thomas
Publikováno v:
Peer Community Journal, Vol 1, Iss , Pp - (2021)
Population genetics have been greatly beneficial to improve knowledge about biological invasions. Model-based genetic inference methods, such as approximate Bayesian computation (ABC), have brought this improvement to a higher level and are now essen
Externí odkaz:
https://doaj.org/article/5ec9c329f99e4abf996a6c32a00b255d
Autor:
Haond, Marjorie, Morel-Journel, Thibaut, Lombaert, Eric, Vercken, Elodie, Mailleret, Ludovic, Roques, Lionel
Publikováno v:
Peer Community Journal, Vol 1, Iss , Pp - (2021)
Finding general patterns in the expansion of natural populations is a major challenge in ecology and invasion biology. Classical spatio-temporal models predict that the carrying capacity (K) of the environment should have no influence on the speed (v
Externí odkaz:
https://doaj.org/article/ed18eed5f06f4ed09a884ce3dc66fcca
Efficiently quantifying predictive uncertainty in medical images remains a challenge. While Bayesian neural networks (BNN) offer predictive uncertainty, they require substantial computational resources to train. Although Bayesian approximations such
Externí odkaz:
http://arxiv.org/abs/2406.06946
We propose a multilevel Markov chain Monte Carlo (MCMC) method for the Bayesian inference of random field parameters in PDEs using high-resolution data. Compared to existing multilevel MCMC methods, we additionally consider level-dependent data resol
Externí odkaz:
http://arxiv.org/abs/2401.15978
Autor:
Murugesan, Balamurali, Vasudeva, Sukesh Adiga, Liu, Bingyuan, Lombaert, Hervé, Ayed, Ismail Ben, Dolz, Jose
Ensuring reliable confidence scores from deep neural networks is of paramount significance in critical decision-making systems, particularly in real-world domains such as healthcare. Recent literature on calibrating deep segmentation networks has res
Externí odkaz:
http://arxiv.org/abs/2401.14487
Autor:
Kamariotis, Antonios, Chatzi, Eleni, Straub, Daniel, Dervilis, Nikolaos, Goebel, Kai, Hughes, Aidan J., Lombaert, Geert, Papadimitriou, Costas, Papakonstantinou, Konstantinos G., Pozzi, Matteo, Todd, Michael, Worden, Keith
Publikováno v:
DCE 5 (2024) e27
To maximize its value, the design, development and implementation of Structural Health Monitoring (SHM) should focus on its role in facilitating decision support. In this position paper, we offer perspectives on the synergy between SHM and decision-m
Externí odkaz:
http://arxiv.org/abs/2402.00021
Autor:
Royer, P., Merle, T., Dsilva, K., Sekaran, S., Van Winckel, H., Frémat, Y., Van der Swaelmen, M., Gebruers, S., Tkachenko, A., Laverick, M., Dirickx, M., Raskin, G., Hensberge, H., Abdul-Masih, M., Acke, B., Alonso, M. L., Mahato, S. Bandhu, Beck, P. G., Behara, N., Bloemen, S., Buysschaert, B., Cox, N., Debosscher, J., De Cat, P., Degroote, P., De Nutte, R., De Smedt, K., de Vries, B., Dumortier, L., Escorza, A., Exter, K., Goriely, S., Gorlova, N., Hillen, M., Homan, W., Jorissen, A., Kamath, D., Karjalainen, M., Karjalainen, R., Lampens, P., Lobel, A., Lombaert, R., Marcos-Arenal, P., Menu, J., Merges, F., Moravveji, E., Nemeth, P., Neyskens, P., Ostensen, R., Pápics, P. I., Perez, J., Royer, S. Prins S., Samadi-Ghadim, A., Sana, H., Fuentes, A. Sans, Scaringi, S., Schmid, V., Siess, L., Siopis, C., Smolders, K., Sodor, S., Thoul, A., Triana, S., Vandenbussche, B., Van de Sande, M., Van De Steene, G., Van Eck, S., van Hoof, P. A. M., Van Marle, A. J., Van Reeth, T., Vermeylen, L., Volpi, D., Vos, J., Waelkens, C.
Publikováno v:
A&A 681, A107 (2024)
Over the past decades, libraries of stellar spectra have been used in a large variety of science cases, including as sources of reference spectra for a given object or a given spectral type. Despite the existence of large libraries and the increasing
Externí odkaz:
http://arxiv.org/abs/2311.02705
Semi-supervised learning relaxes the need of large pixel-wise labeled datasets for image segmentation by leveraging unlabeled data. A prominent way to exploit unlabeled data is to regularize model predictions. Since the predictions of unlabeled data
Externí odkaz:
http://arxiv.org/abs/2310.16099