Metraipolis › archive › dc_08504aba1969

SAREO-FM: Decoupled Semantic Supervision for SAR-EO Foundation Models — arXiv:2610.09317

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09317
License (as archived)
CC0-1.0
Archived
2026-10-08T12:47:06.098Z
SHA-256 of the archived text
c87d8f927967f2d969d3d0e7572b3e73594c0cbc7a149da7134528160f57e4d0
Stable URL of this page
https://metraipolis.com/documento/dc_08504aba1969

How to cite

SAREO-FM: Decoupled Semantic Supervision for SAR-EO Foundation Models — arXiv:2610.09317 — arXiv (en), https://arxiv.org/abs/2610.09317 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08504aba1969 (Metraipolis archive dc_08504aba1969, sha256 c87d8f927967f2d969d3d0e7572b3e73594c0cbc7a149da7134528160f57e4d0)
BibTeX
@misc{dc08504aba1969,
  title = {SAREO-FM: Decoupled Semantic Supervision for SAR-EO Foundation Models — arXiv:2610.09317},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09317},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08504aba1969; sha256 c87d8f927967f2d969d3d0e7572b3e73594c0cbc7a149da7134528160f57e4d0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09317. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Synthetic aperture radar (SAR) and electro-optical (EO) imagery provide complementary observations: SAR enables day-and-night, weather-resilient sensing, whereas EO provides rich appearance and fine-grained semantic cues. We introduce SAREO-FM, which avoids forcing a single token stream to serve two distinct roles: modality tokens preserve how each sensor observes the scene through masked reconstruction, while learnable semantic queries capture what the scene contains under guidance from a pretrained vision foundation model (VFM). By jointly encoding these queries with SAR and EO tokens, the queries acquire modality-grounded semantic context, while the modality-token outputs remain the explicit targets of masked reconstruction. This design assigns semantic and reconstruction supervision to separate token streams while preserving their interaction within the shared encoder. Pretrained on the million-scale SAR-1M corpus, SAREO-FM achieves strong unimodal transfer for both SAR-only and EO-only inputs, while delivering substantial gains from joint SAR--EO observations on tasks that benefit from complementary sensing.

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/2610.09317 — 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 2026-10-08T12:18:15.329Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).