3 papers
cs.LG2026
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…
cs.LG2026
SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings
Léo Nicollier, Max Dunitz, Marc Pic +3
A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. Recently, LeJEPA identified i…
cs.CV2024
Leveraging edge detection and neural networks for better UAV localization
Theo Di Piazza, Enric Meinhardt-Llopis, Gabriele Facciolo +3
We propose a novel method for geolocalizing Unmanned Aerial Vehicles (UAVs) in environments lacking Global Navigation Satellite Systems (GNSS). Current state-of-the-art techniques…