Search Results for author: Benjamin Charlier

Found 11 papers, 2 papers with code

Identify ambiguous tasks combining crowdsourced labels by weighting Areas Under the Margin

no code implementations30 Sep 2022 Tanguy Lefort, Benjamin Charlier, Alexis Joly, Joseph Salmon

We adapt the AUM to identify ambiguous tasks in crowdsourced learning scenarios, introducing the Weighted Areas Under the Margin (WAUM).

Image Classification

IMODAL: Creating Learnable User-Defined Deformation Models

no code implementations CVPR 2021 Leander Lacroix, Benjamin Charlier, Alain Trouve, Barbara Gris

A natural way to model the evolution of an object (growth of a leaf for instance) is to estimate a plausible deforming path between two observations.

Fast geometric learning with symbolic matrices

no code implementations NeurIPS 2020 Jean Feydy, Joan Glaunès, Benjamin Charlier, Michael Bronstein

Geometric methods rely on tensors that can be encoded using a symbolic formula and data arrays, such as kernel and distance matrices.

Kernel Operations on the GPU, with Autodiff, without Memory Overflows

no code implementations27 Mar 2020 Benjamin Charlier, Jean Feydy, Joan Alexis Glaunès, François-David Collin, Ghislain Durif

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.

Prediction of the progression of subcortical brain structures in Alzheimer's disease from baseline

no code implementations23 Nov 2017 Alexandre Bône, Maxime Louis, Alexandre Routier, Jorge Samper, Michael Bacci, Benjamin Charlier, Olivier Colliot, Stanley Durrleman

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.

Parallel transport in shape analysis: a scalable numerical scheme

no code implementations23 Nov 2017 Maxime Louis, Alexandre Bône, Benjamin Charlier, Stanley Durrleman

The analysis of manifold-valued data requires efficient tools from Riemannian geometry to cope with the computational complexity at stake.

White Matter Fiber Segmentation Using Functional Varifolds

no code implementations18 Sep 2017 Kuldeep Kumar, Pietro Gori, Benjamin Charlier, Stanley Durrleman, Olivier Colliot, Christian Desrosiers

We use it to cluster fibers with a dictionary learning and sparse coding-based framework, and present a preliminary analysis using HCP data.

Dictionary Learning

A General Framework for Curve and Surface Comparison and Registration With Oriented Varifolds

no code implementations CVPR 2017 Irene Kaltenmark, Benjamin Charlier, Nicolas Charon

This paper introduces a general setting for the construction of data fidelity metrics between oriented or non-oriented geometric shapes like curves, curve sets or surfaces.


Metamorphoses of functional shapes in Sobolev spaces

1 code implementation5 Aug 2016 Nicolas Charon, Benjamin Charlier, Alain Trouvé

In this paper, we describe in detail a model of geometric-functional variability between fshapes.

Optimization and Control Differential Geometry 49M25, 49Q20, 58B32, 58E50, 68U05, 68U10

The fshape framework for the variability analysis of functional shapes

no code implementations24 Apr 2014 Benjamin Charlier, Nicolas Charon, Alain Trouvé

This article introduces a full mathematical and numerical framework for treating functional shapes (or fshapes) following the landmarks of shape spaces and shape analysis.

Cannot find the paper you are looking for? You can Submit a new open access paper.