Metraipolis › archive › dc_cf12ce22e0fc
FieldGuideRAG: Image-Grounded GraphRAG for Fine-Grained Recognition with Vision-Language Models — arXiv:2610.40971
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40971
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T05:02:52.723Z
- SHA-256 of the archived text
653ba8706440200690b9844da0d51d8f92dd140863cdf3edb0dbb32a782e7cca- Stable URL of this page
https://metraipolis.com/documento/dc_cf12ce22e0fc
How to cite
FieldGuideRAG: Image-Grounded GraphRAG for Fine-Grained Recognition with Vision-Language Models — arXiv:2610.40971 — arXiv (en), https://arxiv.org/abs/2610.40971 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf12ce22e0fc (Metraipolis archive dc_cf12ce22e0fc, sha256 653ba8706440200690b9844da0d51d8f92dd140863cdf3edb0dbb32a782e7cca)
BibTeX
@misc{dccf12ce22e0fc,
title = {FieldGuideRAG: Image-Grounded GraphRAG for Fine-Grained Recognition with Vision-Language Models — arXiv:2610.40971},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40971},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf12ce22e0fc; sha256 653ba8706440200690b9844da0d51d8f92dd140863cdf3edb0dbb32a782e7cca},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40971. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present FieldGuideRAG, a training-free GraphRAG method in which a vision-language model, or VLM, recognizes fine-grained species by comparing the query with real photographs stored on the nodes of a knowledge graph. Multimodal GraphRAG systems describe each entity in text, and text conveys little of the visual detail that separates look-alike species. Our graph stores one photograph on every species node and links each species to its relatives, its geographic range and its ecological facts. A frozen VLM verifies the query against the photograph of each candidate node. FieldGuideRAG fuses the verification scores with the range edge and answers questions about the organism from the fact edges of the verified species. On CUB-200, a Wikidata graph and four iNaturalist domains, the node photograph improves verification over the species name on every graph, while text descriptions add little. Verification of the candidate pool exceeds a SigLIP retriever by up to 16 points, the range edge adds 7 to 19 points on iNaturalist, and answering from fact edges is correct on up to 89.5% of 28,820 ecological questions. The verification scores also detect queries whose species is missing from the graph. Graphs, prompts and code will be released. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2610.40971 — 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 2026-11-02T04:48:58.169Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).