I am a phd student in machine learning at Université de Montpellier in IMAG, under the supervision of Joseph Salmon, Alexis Joly and Maximilien Servajean.
I am also hosted by INRIA in the ZENITH team.
I graduated from Centrale Paris and got a Msc in Machine Learning from ENS Paris Saclay.
Pl@ntNet-300K is a dataset of 306,146 plant images covering 1,081 species. It has high inter-class ambiguity and intra-class variability, and a long-tailed distribution. You can download it here. The paper describing the dataset can be found here.
A two-head loss function for deep Average-K classification
Camille Garcin, Maximilien Servajean, Alexis Joly, Joseph Salmon
Preprint
[pdf]
Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification
Camille Garcin, Maximilien Servajean, Alexis Joly, Joseph Salmon
ICML2022
[pdf][code]
Pl@ntNet-300K: a plant image dataset with high label ambiguity and a long-tailed distribution
Camille Garcin, Alexis Joly, Pierre Bonnet, Antoine Affouard, Jean-Christophe Lombardo, Mathias Chouet, Maximilien Servajean, Titouan Lorieul
NeurIPS2021, Datasets and Benchmark track
[pdf][code][dataset]
PHD Seminar
IMAG, Montpellier (France), September 2022
Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification (Talk)
ICML2022
Baltimore (USA), July 2022
Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification (Talk) [video][poster]
CAp2022
Vannes (France), July 2022
Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification (Talk)
Journées de Statistique
Lyon (France), June 2022
Pl@ntNet-300K: a plant image dataset with high label ambiguity and a long-tailed distribution (Talk)
EPS Team Seminar
IMAG, Montpellier (France), May 2022
Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification (Talk)
NeurIPS2021
Virtual, December 2021
Pl@ntNet-300K: a plant image dataset with high label ambiguity and a long-tailed distribution (Talk) [video]
NeurIPS@Paris 2021
SCAI, Paris, December 2021
Pl@ntNet-300K: a plant image dataset with high label ambiguity and a long-tailed distribution (Talk)
Journée Cemeb-NUMEV "IA & Biodiversité"
Virtual, January 2021
Top-k Loss for Plant Classification (Talk)
Université de Montpellier
2022 - 2023 Probability L1 - HAV220X (32 hours)
2021 - 2022 Probability L1 - HAV220X (32 hours)
2020 - 2021 Statistics L2 - HLMA314 (32 hours) HLMA315 (32 hours)
Here is my GitHub.
You can contact me at firstname.lastname@inria.fr.
