Nicolas Courty

Nicolas Courty

Professor in Computer Science

Université Bretagne Sud / IRISA

Biography

Welcome ! I am a Full Professor at University Bretagne Sud since 2018. I obtained my PhD degree in 2002 from INSA Rennes and my 'Habilitation à diriger des recherches' in 2013, on the topic of computer graphics and animation (avatars, crowds), with a specialization in data-driven methods. I now lead the Obelix team at IRISA, which research contributions lie at the crossroad of machine learning and Earth Observation. I am an experienced researcher in the domain of machine learning and AI. Among others, I have published several papers in top tier machine learning conferences (NeurIPS, ICLR, ICML, AISTATS, etc.), computer vision (IEEE TPAMI, ECCV, ACCV) and remote sensing (IEEE TGRS, ISPRS journal). From 2014, I developed an expertise in the domain of optimal transport and related applications to machine learning. From 2020, I am the principal investigator in an ANR Chair program on AI (OTTOPIA), on the topic of applied optimal transport for Remote Sensing.

Scientific interests:

  • Optimal transport, Statistical learning, kernel methods
  • Manifold and geometric approaches to machine learning
  • Applications to computer graphics, vision and remote sensing

Code production

As a computer scientist, I definitely believe in the power of open-source and reproducibility as a basis of science. Though my current activities will not let me hand on code as much as I want to, I still enjoy coding in C++, Cuda kernels or PyTorch. Take a look at the coding section to know more.

Other publications

(2024). Domain Adaptation of Time Series through Optimal Transport and Temporal Alignment. 55ièmes Journées de Statistique.

Cite URL

(2024). Apprentissage contrastif multi-modal: Du pré-entrainement auto-supervisé à la classification supervisée.. Joint CAP and RFIAP 2024 Conferences.

Cite

(2024). Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein Projection. arXiv preprint arXiv:2402.02239.

Cite

(2024). Domain Adaptation of Time Series through Optimal Transport and Temporal Alignment. 55ièmes Journées de Statistique.

Cite

(2024). Non Euclidean Sliced Optimal Transport Sampling Software.

Cite URL