8 papers
Beyond Gaussian Worlds: Latent Geometry Matters for JEPAs
Léo Nicollier, Enric Meinhardt-Llopis, Marc Pic +2
Recent Joint-Embedding Predictive Architectures (JEPAs) prevent representation collapse by constraining learned representations to follow a prescribed target distribution, such as…
Efficient Neural-Network-Based High-Resolution Radiative Transfer for CO___ Retrieval, and Application to Interferometric Sensing
Jordan Lontsi Tedongmo, Yann Ferrec, Laurence Croizé +3
Studying climate change requires reducing uncertainties in CO2 and CH4 emission estimates to better distinguish anthropogenic from natural sources, which motivates spaceborne measu…
Unbiased Open World Regularization for Fair Self-Supervised Learning
L{é}o Nicollier, Marc Pic, Pablo Mus{é} +2
Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to learning spurious biases in the dataset. T…
Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere
Léo Nicollier, Enric Meinhardt-Llopis, Max Dunitz +3
In Self-Supervised Learning (SSL), preventing representation collapse by explicitly enforcing a uniform distribution on the unit hypersphere has proven to be effective. However, cu…
Deep S2P: Integrating Learning Based Stereo Matching Into the Satellite Stereo Pipeline
Elías Masquil, Thibaud Ehret, Pablo Musé +1
Digital Surface Model generation from satellite imagery is a core task in Earth observation and is commonly addressed using classical stereoscopic matching algorithms in satellite…
Diachronic Stereo Matching for Multi-Date Satellite Imagery
Elías Masquil, Luca Savant Aira, Roger Marí +3
Recent advances in image-based satellite 3D reconstruction have progressed along two complementary directions. On one hand, multi-date approaches using NeRF or Gaussian-splatting j…
S-EO: A Large-Scale Dataset for Geometry-Aware Shadow Detection in Remote Sensing Applications
Elías Masquil, Roger Marí, Thibaud Ehret +3
We introduce the S-EO dataset: a large-scale, high-resolution dataset, designed to advance geometry-aware shadow detection. Collected from diverse public-domain sources, including…
Graph Contrastive Learning for Connectome Classification
Martín Schmidt, Sara Silva, Federico Larroca +2
With recent advancements in non-invasive techniques for measuring brain activity, such as magnetic resonance imaging (MRI), the study of structural and functional brain networks th…