Zobrazeno 1 - 10
of 50
pro vyhledávání: '"CHARLIER, BENJAMIN"'
Autor:
Lefort, Tanguy, Affouard, Antoine, Charlier, Benjamin, Lombardo, Jean-Christophe, Chouet, Mathias, Goëau, Hervé, Salmon, Joseph, Bonnet, Pierre, Joly, Alexis
Deep learning models for plant species identification rely on large annotated datasets. The PlantNet system enables global data collection by allowing users to upload and annotate plant observations, leading to noisy labels due to diverse user skills
Externí odkaz:
http://arxiv.org/abs/2406.03356
In supervised learning - for instance in image classification - modern massive datasets are commonly labeled by a crowd of workers. The obtained labels in this crowdsourcing setting are then aggregated for training, generally leveraging a per-worker
Externí odkaz:
http://arxiv.org/abs/2209.15380
Autor:
Moreau, Thomas, Massias, Mathurin, Gramfort, Alexandre, Ablin, Pierre, Bannier, Pierre-Antoine, Charlier, Benjamin, Dagréou, Mathieu, la Tour, Tom Dupré, Durif, Ghislain, Dantas, Cassio F., Klopfenstein, Quentin, Larsson, Johan, Lai, En, Lefort, Tanguy, Malézieux, Benoit, Moufad, Badr, Nguyen, Binh T., Rakotomamonjy, Alain, Ramzi, Zaccharie, Salmon, Joseph, Vaiter, Samuel
Numerical validation is at the core of machine learning research as it allows to assess the actual impact of new methods, and to confirm the agreement between theory and practice. Yet, the rapid development of the field poses several challenges: rese
Externí odkaz:
http://arxiv.org/abs/2206.13424
Autor:
Charlier, Benjamin, Feydy, Jean, Glaunès, Joan Alexis, Collin, François-David, Durif, Ghislain
Publikováno v:
Journal of Machine Learning Research 22, 1-6 (2021). https://jmlr.org/papers/v22/20-275.html
The KeOps library provides a fast and memory-efficient GPU support for tensors whose entries are given by a mathematical formula, such as kernel and distance matrices. KeOps alleviates the major bottleneck of tensor-centric libraries for kernel and g
Externí odkaz:
http://arxiv.org/abs/2004.11127
The analysis of manifold-valued data requires efficient tools from Riemannian geometry to cope with the computational complexity at stake. This complexity arises from the always-increasing dimension of the data, and the absence of closed-form express
Externí odkaz:
http://arxiv.org/abs/1711.08725
Autor:
Bône, Alexandre, Louis, Maxime, Routier, Alexandre, Samper, Jorge, Bacci, Michael, Charlier, Benjamin, Colliot, Olivier, Durrleman, Stanley
We propose a method to predict the subject-specific longitudinal progression of brain structures extracted from baseline MRI, and evaluate its performance on Alzheimer's disease data. The disease progression is modeled as a trajectory on a group of d
Externí odkaz:
http://arxiv.org/abs/1711.08716
Autor:
Kumar, Kuldeep, Gori, Pietro, Charlier, Benjamin, Durrleman, Stanley, Colliot, Olivier, Desrosiers, Christian
Publikováno v:
Graphs in Biomedical Image Analysis, Computational Anatomy and Imaging Genetics, pp 92-100, Lecture Notes in Computer Science, volume 10551, Springer, 2017
The extraction of fibers from dMRI data typically produces a large number of fibers, it is common to group fibers into bundles. To this end, many specialized distance measures, such as MCP, have been used for fiber similarity. However, these distance
Externí odkaz:
http://arxiv.org/abs/1709.06144
This paper introduces the use of unbalanced optimal transport methods as a similarity measure for diffeomorphic matching of imaging data. The similarity measure is a key object in diffeomorphic registration methods that, together with the regularizat
Externí odkaz:
http://arxiv.org/abs/1706.05218
In this paper, we describe in detail a model of geometric-functional variability between fshapes. These objects were introduced for the first time by the authors in [Charlier et al. 2015] and are basically the combination of classical deformable mani
Externí odkaz:
http://arxiv.org/abs/1608.01832
Publikováno v:
Interfaces & Free Boundaries; 2024, Vol. 26 Issue 3, p381-414, 34p