Maarten Vergauwen — accepted AI-conference papers

2026

NeighborMAE: Exploiting Spatial Dependencies between Neighboring Earth Observation Images in Masked Autoencoders Pretraining

Liang Zeng, Valerio Marsocci, Wufan Zhao, Andrea Nascetti, Maarten Vergauwen

CVPR 2026

Masked Image Modeling has been one of the most popular self-supervised learning paradigms to learn representations from large-scale, unlabeled Earth Observation images. While incorporating multi-modal and multi-temporal Earth Observation data into Masked Image Modeling has been widely explored, the

Cited by 0 Source ↗code ↗Scholar ↗

2025

Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?

Yuru Jia, Valerio Marsocci, Ziyang Gong, Xue Yang, Maarten Vergauwen, Andrea Nascetti

ICCV 2025poster

Self-supervised learning (SSL) has revolutionized representation learning in Remote Sensing (RS), advancing Geospatial Foundation Models (GFMs) to leverage vast unlabeled satellite imagery for diverse downstream tasks. Currently, GFMs primarily employ objectives like contrastive learning or masked i…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗