Metraipolis › archive › dc_5ce4f4288128

When GeoFMs Meet VHR: Benchmarking Foundation Models on Very High Resolution Earth Observation Imagery — arXiv:2611.08003

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08003
License (as archived)
CC0-1.0
Archived
2026-11-06T14:53:39.342Z
SHA-256 of the archived text
bc20f7d6ec20de63286fabff4cbe5e666915ddbbd251dc0f6da6c34fe739647c
Stable URL of this page
https://metraipolis.com/documento/dc_5ce4f4288128

How to cite

When GeoFMs Meet VHR: Benchmarking Foundation Models on Very High Resolution Earth Observation Imagery — arXiv:2611.08003 — arXiv (en), https://arxiv.org/abs/2611.08003 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ce4f4288128 (Metraipolis archive dc_5ce4f4288128, sha256 bc20f7d6ec20de63286fabff4cbe5e666915ddbbd251dc0f6da6c34fe739647c)
BibTeX
@misc{dc5ce4f4288128,
  title = {When GeoFMs Meet VHR: Benchmarking Foundation Models on Very High Resolution Earth Observation Imagery — arXiv:2611.08003},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08003},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ce4f4288128; sha256 bc20f7d6ec20de63286fabff4cbe5e666915ddbbd251dc0f6da6c34fe739647c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08003. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Geospatial foundation models are a widely adopted starting point for remote sensing tasks. Most are pretrained on Sentinel-1/2 and Landsat imagery at a ground sampling distance (GSD) of 10m or coarser. Many applications instead rely on very high resolution (VHR) imagery, where individual buildings, roads, and amenities are resolved. We study which pretraining regimes transfer well to this scale. We introduce VHR-Bench, a benchmark suite of ten datasets at 1.5m GSD or finer spanning five task families, eight application domains, and both satellite and aerial platforms. We evaluate twelve encoders in three pretraining tiers with frozen backbones at two training-data fractions. We find that both pretraining on large natural-image collections and VHR-specific pretraining transfer effectively to VHR tasks, with complementary strengths. SkySense leads when labels are scarce; at the full label fraction the web-pretrained DINOv3 ViT-L edges ahead, with the two close together there. Encoders pretrained only on Sentinel-scale imagery transfer least well under RGB input. Guided by these complementary results, we continue the self-supervised pretraining of DINOv3 ViT-L on 1.02 million held-out VHR tiles and evaluate the resulting encoder without changing the downstream protocol. The continued model gives a clear improvement over the released backbone when labels are scarce and a modest one at the full fraction, at no increase in inference parameters or compute. These findings support a generalize-then-specialize strategy: already strong, broad natural-image pretraining can be further improved by a short VHR continuation stage while preserving its general visual features.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.08003 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-06T14:25:42.623Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).