Guillaume Astruc, Nicolas Gonthier, Clément Mallet and Loic Landrieu

PDF - Code - HF Page - Project Page

Abstract

Geospatial models must adapt to the diversity of Earth observation data in terms of resolutions, scales, and modalities. However, existing approaches expect fixed input configurations, which limits their practical applicability. We propose ManySat, a multimodal model based on joint embedding predictive architecture (JEPA) and resolution-adaptive spatial encoders, allowing us to train a single model on highly heterogeneous data in a self-supervised manner. To demonstrate the advantages of this unified approach, we compile GeoPlex, a collection of 5 multimodal datasets with varying characteristics and 11 distinct sensors. We then train a single powerful model on these diverse datasets simultaneously. Once fine-tuned, we achieve better or near state-of-the-art results on the datasets of GeoPlex and 4 additional ones for 5 environment monitoring tasks: land cover mapping, tree species identification, crop type classification, change detection, and flood segmentation.

Keywords

• Multi modalities
• Modalities fusion
• Aerial Images
• Satellite Times Series
• Self-supervised learning