11 citations · 45 across the 21 of their papers we have counts for
21 papers
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…
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…
Black carbon plumes from gas flaring in North Africa identified from multi-spectral imagery with deep learning
Tuel Alexandre, Kerdreux Thomas, Thiry Louis
Black carbon (BC) is an important pollutant aerosol emitted by numerous human activities, including gas flaring. Improper combustion in flaring activities can release large amounts…
Strong Convexity of Sets in Riemannian Manifolds
Damien Scieur, David Martínez-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.…
Autonomous Detection of Methane Emissions in Multispectral Satellite Data Using Deep Learning
Bertrand Rouet-Leduc, Thomas Kerdreux, Alexandre Tuel +1
Methane is one of the most potent greenhouse gases, and its short atmospheric half-life makes it a prime target to rapidly curb global warming. However, current methane emission mo…
Diffusion Models for Interferometric Satellite Aperture Radar
Alexandre Tuel, Thomas Kerdreux, Claudia Hulbert +1
Probabilistic Diffusion Models (PDMs) have recently emerged as a very promising class of generative models, achieving high performance in natural image generation. However, their p…
Acceleration of Frank-Wolfe Algorithms with Open-Loop Step-Sizes
Elias Wirth, Thomas Kerdreux, Sebastian Pokutta
Frank-Wolfe algorithms (FW) are popular first-order methods for solving constrained convex optimization problems that rely on a linear minimization oracle instead of potentially ex…
Efficient Online-Bandit Strategies for Minimax Learning Problems
Christophe Roux, Elias Wirth, Sebastian Pokutta +1
Several learning problems involve solving min-max problems, e.g., empirical distributional robust learning or learning with non-standard aggregated losses. More specifically, these…
Linear Bandits on Uniformly Convex Sets
Thomas Kerdreux, Christophe Roux, Alexandre d'Aspremont +1
Linear bandit algorithms yield pseudo-regret bounds on compact convex action sets and two types of structural assu…
Local and Global Uniform Convexity Conditions
Thomas Kerdreux, Alexandre d'Aspremont, Sebastian Pokutta
We review various characterizations of uniform convexity and smoothness on norm balls in finite-dimensional spaces and connect results stemming from the geometry of Banach spaces w…
Generating Structured Adversarial Attacks Using Frank-Wolfe Method
Ehsan Kazemi, Thomas Kerdreux, Liquang Wang
White box adversarial perturbations are generated via iterative optimization algorithms most often by minimizing an adversarial loss on a neighborhood of the original imag…
Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets
Thomas Kerdreux, Lewis Liu, Simon Lacoste-Julien +1
It is known that the Frank-Wolfe (FW) algorithm, which is affine-covariant, enjoys accelerated convergence rates when the constraint set is strongly convex. However, these results…
Diptychs of human and machine perceptions
Vivien Cabannes, Thomas Kerdreux, Louis Thiry
We propose visual creations that put differences in algorithms and humans \emph{perceptions} into perspective. We exploit saliency maps of neural networks and visual focus of human…
Trace-Norm Adversarial Examples
Ehsan Kazemi, Thomas Kerdreux, Liqiang Wang
White box adversarial perturbations are sought via iterative optimization algorithms most often minimizing an adversarial loss on a neighborhood of the original image, the so…
Projection-Free Optimization on Uniformly Convex Sets
Thomas Kerdreux, Alexandre d'Aspremont, Sebastian Pokutta
The Frank-Wolfe method solves smooth constrained convex optimization problems at a generic sublinear rate of , and it (or its variants) enjoys accelerated converg…
Interactive Neural Style Transfer with Artists
Thomas Kerdreux, Louis Thiry, Erwan Kerdreux
We present interactive painting processes in which a painter and various neural style transfer algorithms interact on a real canvas. Understanding what these algorithms' outputs ac…
Dialog on a canvas with a machine
Vivien Cabannes, Thomas Kerdreux, Louis Thiry +2
We propose a new form of human-machine interaction. It is a pictorial game consisting of interactive rounds of creation between artists and a machine. They repetitively paint one a…
Restarting Frank-Wolfe: Faster Rates Under Hölderian Error Bounds
Thomas Kerdreux, Alexandre d'Aspremont, Sebastian Pokutta
Conditional Gradient algorithms (aka Frank-Wolfe algorithms) form a classical set of methods for constrained smooth convex minimization due to their simplicity, the absence of proj…
Reconstructing Latent Orderings by Spectral Clustering
Antoine Recanati, Thomas Kerdreux, Alexandre d'Aspremont
Spectral clustering uses a graph Laplacian spectral embedding to enhance the cluster structure of some data sets. When the embedding is one dimensional, it can be used to sort the…
Frank-Wolfe with Subsampling Oracle
Thomas Kerdreux, Fabian Pedregosa, Alexandre d'Aspremont
We analyze two novel randomized variants of the Frank-Wolfe (FW) or conditional gradient algorithm. While classical FW algorithms require solving a linear minimization problem over…
An Approximate Shapley-Folkman Theorem
Thomas Kerdreux, Igor Colin, Alexandre d'Aspremont
The Shapley-Folkman theorem shows that Minkowski averages of uniformly bounded sets tend to be convex when the number of terms in the sum becomes much larger than the ambient dimen…