Metraipolis › archive › dc_4e01c25ea726
GeoNLI - A Natural Language Interpreter for Satellite Imagery — arXiv:2609.28741
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28741
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T06:44:14.465Z
- SHA-256 of the archived text
355bae3d5e6f0e34259c4abb1e2f047c4895ad63b3520ba557a88c8f781a4211- Stable URL of this page
https://metraipolis.com/documento/dc_4e01c25ea726
How to cite
GeoNLI - A Natural Language Interpreter for Satellite Imagery — arXiv:2609.28741 — arXiv (en), https://arxiv.org/abs/2609.28741 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e01c25ea726 (Metraipolis archive dc_4e01c25ea726, sha256 355bae3d5e6f0e34259c4abb1e2f047c4895ad63b3520ba557a88c8f781a4211)
BibTeX
@misc{dc4e01c25ea726,
title = {GeoNLI - A Natural Language Interpreter for Satellite Imagery — arXiv:2609.28741},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28741},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e01c25ea726; sha256 355bae3d5e6f0e34259c4abb1e2f047c4895ad63b3520ba557a88c8f781a4211},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28741. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-modal multitasking models have shown strong performance on remote sensing datasets. However, because these models are trained on heterogeneous data and vary across tasks, designing a unified model that performs well in captioning, visual question answering (VQA), and visual grounding remains challenging. In this work, we evaluate several models on the VRS Bench and NWPU-VHR-10 datasets. The EarthMind model demonstrates strong results in both captioning and VQA. For grounding, we propose multiple pipelines - RemoteSAM-SAM-v1, RemoteSAM-SAM-v2, and DiffuSAM - and ultimately adopt a majority-voting ensemble across EarthMind, RemoteSAM, SAM3, Falcon, RemoteSAM-SAM3-v1, RemoteSAM-SAM3-v2, and DiffuSAM predictions. Our unified, modular pipeline integrates advanced SAM variants with multimodal LLMs to jointly perform captioning, VQA, and grounding. It achieves 82% accuracy on captioning and 83.32% on VQA, with 90.94%, 52.04%, and 92.06% for binary, numeric, and semantic question types respectively. For grounding, it attains 64.94% accuracy. By combining diverse VLMs with our custom RemoteSAM-SAM3 models through ensemble majority voting, the system delivers more accurate and consistent remote-sensing understanding than task-specific approaches. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.28741 — 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 2026-10-08T06:09:29.777Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).