New Study Uses Positive-Unlabeled Learning to Adapt Geospatial Foundation Models for Building Damage Mapping

A new arXiv paper proposes adapting geospatial foundation models to building damage mapping with positive-unlabeled learning, reducing the need for labeled training data in remote sensing tasks.

Read the full story at arXiv cs.CV ↗

Timeline · 1 report

1. 2026-11-10 05:00 · arXiv cs.CV
   Towards Label-Efficient Geospatial Foundation Model Adaptation via Positive-Unlabeled Learning for Building Damage Mapping