Segolene Martin homepage

Ségolène Martin

Email Github Scholar CV

I am a tenured researcher (Chargée de Recherche) at Inria Lyon in the OCKHAM team.
My current research is at the intersection of optimization and generative learning, with applications to image processing and computer vision.
Previously, I was a postdoctoral researcher at TU Berlin, in the team headed by Prof. Gabriele Steidl. I completed my PhD in applied mathematics at CentraleSupélec, Université Paris-Saclay, in the CVN / OPIS Inria team. I did my PhD under the supervision of Prof. Jean-Christophe Pesquet (CVN, CentraleSupélec) and Prof. Ismail Ben Ayed (ILLS, ETS Montréal).

Research interests

Generative modeling
Flow-based methods (mainly) for imaging
Inverse problems for imaging
Image restoration and reconstruction in the Bayesian framework
Classification
Clustering and few-shot optimization-based methods, transductive learning,
text-vision models
Large-scale continuous optimization
Proximal algorithms, subspace acceleration, convergence theory

Education

PhD in Applied Mathematics, 2020-2024
CentraleSupélec, Université Paris-Saclay
Master in Mathematics, Vision and Learning (MVA), 2019-2020
École Normale Supérieure Paris-Saclay
Agrégation in Mathematics, 2018-2019
École Normale Supérieure Paris-Saclay
Bachelor's Degree in Fundamental Mathematics, 2016-2017
École Normale Supérieure Paris-Saclay

Publications

Publication preceeded with a * are the ones where I am a main author.

Submitted papers

*S. Martin, A. Gagneux, Q. Bertrand, R. Emonet, M. Massias, Beyond the Manifold Hypothesis: Hybrid Spectral Parameterizations for Flow Matching , arXiv preprint arXiv:2609.32432.
A. Lagier, V. Tosel, A. Gagneux, M. Massias, S. Martin Principled MAP estimation for inverse problems: bridging the gap between convergence and performance , arXiv preprint arXiv:2609.37529.

Journal articles

C. Drygala, H. Gottschalk, T. Kruse, S. Martin, A. Muetze, Learning Brenier Potentials with Convex Generative Adversarial Neural Networks , Mathematical Foundations of Machine Learning .
*S. Martin, J.-C. Pesquet, G. Steidl, I. Ben Ayed, Variable Bregman Majorization-Minimization Algorithm and its Application to Dirichlet Maximum Likelihood Estimation , Journal of Applied and Numerical Optimization.
* J. Ajdenbaum, E. Chouzenoux, S. Martin, C. Lefort, J.-C. Pesquet, A novel variational approach for multiphoton microscopy image restoration: from PSF estimation to 3D deconvolution, Inverse Problems, 2024.
J.-B. Fest, T. Heikkilä, I. Loris, S. Martin, L. Ratti, S. Rebegoldi, G. Sarnighausen, On a fixed- point continuation method for a convex optimization problem, Advanced Techniques in Optimization for Machine learning and Imaging (ATOMI), 2023.
*E. Chouzenoux, S. Martin, J.-C. Pesquet, A local MM subspace method for solving constrained variational problems in image recovery Journal of Mathematical Imaging and Vision, 2022.

Conference Proceedings

M. S. Ben Omrane, S. Martin, M. Kaaniche, A. Laurent-Bellue, W. M. Souid, C. Guettier, and J.-C. Pesquet Making HE Histopathological Images More Colorful by Conditional Flow Matching , MICCAI, 2026.
A. Clerc, S. Martin, N. Papadakis, G. Steidl, Reinterpreting EMML as Mirror Descent for Constrained Maximum Likelihood Estimation, EUSIPCO, 2026.
*A. Gagneux, S. Martin, R. Gribonval, M. Massias, Training flow matching: The role of weighting and parameterization , ICLR Delta Workshop, 2026.
*S. Martin, A. Gagneux, P. Hagemann, G. Steidl, PnP-Flow: Plug-and-Play Image Restoration with Flow Matching., to appear in ICLR, 2025.
M. Adipoetra, S. Martin, Deep Generative Clustering with VAEs and Expectation-Maximization , to appear in International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) (oral), 2025.
*S. Martin, Y. Huang, F. Shakeri, J.-C. Pesquet, I. Ben Ayed, Transductive zero-shot and few-shot CLIP, CVPR as a highlight (<10 % of papers), 2024.
*A. Sadraoui, S. Martin, E. Barbot, A. Laurent-Bellue, J.-C. Pesquet, C. Guettier, A transductive few-shot learning approach for classification of liver cancer histopathology images, IEEE International Symposium on Biomedical Imaging (ISBI), 2024.
*S. Martin, M. Boudiaf, E. Chouzenoux, J.-C. Pesquet, I. Ben Ayed, Towards practical few-shot query sets : Transductive minimum description length inference, NeurIPS, 2022.
M. Kahanam, L. Le-Brusquet, S. Martin, J.-C. Pesquet, A Non-Convex Proximal Approach for Centroid-Based Classification, ICASSP, 2022.
*S. Martin, E. Chouzenoux, J.-C. Pesquet, A Penalized Subspace Strategy for Solving Large-Scale Constrained Optimization Problems, EUSIPCO, 2021.

Thesis

S. Martin, Variational methods for large scale data problems in imaging (26.01.2024)

Scientific Activities

October 2026 - Co-organizer, with Mathurin Massias, of the GdR IASIS day on generative models.
July 2026 - Course on generative models for inverse problems at the Peyresq Summer School.
May 2026 - Invited speaker at ICMS, Edinburgh, with the talk Flow Matching Meets Denoising: A Plug-and-Play Approach to Inverse Problems.
April 2026 - Invited speaker at Statlearn Conference, Grenoble, with the talk Flow Matching Meets Denoising: A Plug-and-Play Approach to Inverse Problems.
March 2026 - Hosted for one week at CIRM for a BOUM project with Anne Gagneux and Quentin Bertrand.
March 2026 - Awarded a €9,000 grant from GdR IASIS through the AAP 2026 call.

I am also involved in several teaching activities. I have been a teaching for the following courses:

Generative models, Master 2, ENS Lyon, 2026 - course taught with Quentin Bertrand and Mathurin Massias
Refresher course on optimization, Master 2 MVA, ENS Paris-Saclay, 2020-2023 - course taught by J.-C. Pesquet (exercises, correction)
Optimization, Master 1, CentraleSupelec, 2023 - course taught by J.-C. Pesquet
Data analysis and statistics, Bachelor 1, IUT Orsay, 2022 - course taught by S. Marduel
Python, Bachelor 1, IUT Orsay, 2022 - course taught by S. Marduel
Signal processing, Bachelor 2, IUT Orsay, 2021 - course taught by F. Alberge
Data analysis and statistics, Bachelor 1, IUT Orsay, 2021 - course taught by T. Guilbaud
Python, Bachelor 1, IUT Orsay, 2021 - course taught by T. Guilbaud
Mathematics, Bachelor 1, IUT Orsay, 2020 - course taught by M. Lagron
Oral interrogations in mathematics in "Classes Préparatoires aux Grandes Ecoles", Lycée Saint Louis, Paris, 2019-2020