SOURCE-LINKED INTELLIGENCE
Reuse, Don't Retrain: Efficient, Modality-Versatile Geospatial Foundation Models through Feature Distillation
Geospatial foundation models (GeoFMs) are costly to pretrain, yet model families often repeat this process across backbone scales and sensing modalities. We investigate feature distillation as a more efficient way to reuse existing representations. First, we distill frozen CROMA and TerraMind teachers into smaller Vision Transformers through patch-level feature matching. Across nine PANGAEA tasks, distilled TerraMind Tiny, Small, and Base outperform their scale-matched released counterparts by 2.76, 3.02, and 1.87 mean IoU points, respectively; each also matches or exceeds the next-larger rele
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-10-23T12:48:24.000Z
First collected: 2026-10-26T05:16:32.604Z. This is not the publication date.