3 papers
cs.LG2026
OceanSAR-2: A Universal Feature Extractor for SAR Ocean Observation
Alexandre Tuel, Thomas Kerdreux, Quentin Febvre +6
We present OceanSAR-2, the second generation of our foundation model for SAR-based ocean observation. Building on our earlier release, which pioneered self-supervised learning on S…
cs.CV2025
Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation
Thomas Kerdreux, Alexandre Tuel, Quentin Febvre +2
Self-supervised learning (SSL) has enabled the development of vision foundation models for Earth Observation (EO), demonstrating strong transferability across diverse remote sensin…
math.OC2024
Strong Convexity of Sets in Riemannian Manifolds
Damien Scieur, David MartÃnez-Rubio, Thomas Kerdreux +2
Curvature properties of convex objects, such as strong convexity, are important in designing and analyzing convex optimization algorithms in the Hilbertian or Riemannian settings.…