cs.CVOct 29, 2026

FieldGuideRAG: Image-Grounded GraphRAG for Fine-Grained Recognition with Vision-Language Models

Authors: Jiacheng Ding, Yanliang Qi, Cong Guo, Peihua Mai

Organizations: University of Memphis · National University of Singapore

Abstract

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.

Figures & tables

Explore similar work

Sep 10, 2026

Can Edge-Deployable Vision-Language Models Identify Species?

Camera traps often run in the field on edge hardware with limited or no connectivity, making small, locally-deployable vision-language models (VLMs) -- not frontier-scale ones -- the practically relevant class to evaluate for species identification. We test whether models in this deployment-relevant 2--8B range carry genuine taxonomic knowledge, evaluating four such VLMs (Qwen3-VL 2B/4B/8B, Gemma3 4B) against the domain-specific specialist BioCLIP (300M parameters) on a 96-species task, comparing clean iNaturalist photographs against camera-trap imagery from 6 LILA.science collections, on two independently-sampled evaluation sets. All models identify species far above chance, but every model -- general-purpose or specialist -- degrades sharply on field imagery (domain gaps of 9.6--26.6 percentage points, consistent across taxonomic levels and both evaluation sets), indicating the degradation reflects general image legibility rather than fine-grained discrimination failure. BioCLIP substantially outperforms every VLM tested (by 33.2--59.2 percentage points across an expanded 200-image sample for every model) despite its far smaller size, suggesting the gap reflects specialized training data rather than model scale; yet BioCLIP's own domain gap (18.0 points) is statistically indistinguishable from the best VLM's (22.3 points), suggesting the clean-to-field degradation itself is a property of the image-quality shift rather than a general-purpose-model weakness. Under open-set prompting, 5.9--9.6% of responses are syntactically valid but taxonomically nonexistent species names; the relative fabrication-rate ranking across models replicates exactly across both evaluation sets, a more robust finding than any single point estimate.
Nov 3, 2026

How Finely Can Vision-Language Models See Biology? Bio-VQA: A Benchmark for Taxonomic, Morphological, Spatial and Individual Reasoning

In biodiversity monitoring, a single image raises several questions: which taxon, how many, which trait, and whether the individual has been seen before. Vision-language models (VLMs) could answer all of these from the image, but their ability is largely untested in biology, as existing benchmarks focus mostly on species identification within a few taxonomic groups. We present Bio-VQA, the largest biological visual question answering (VQA) benchmark and the only one to span four aspects of biological visual understanding: hierarchical taxonomic reasoning, fine-grained attribute grounding, quantitative spatial reasoning, and individual re-identification. Bio-VQA contains 1.86M questions over 217K images from 11 public datasets, and extends right-or-wrong scoring to graded scoring, so a near-miss counts for more than a distant one. Evaluating 18 open-weight models from 3.75B to 38.4B parameters, we find that general visual capabilities do not transfer to biological organisms: the best model counts animals exactly on 41.7% of images with 2 to 10 individuals, less than half its accuracy on everyday objects at the same counts. Taxonomic accuracy falls to one sixth, from 0.72 at phylum to 0.12 at scientific name, and scaling helps mostly at coarse ranks. The gap to a domain specialist widens accordingly, from 0.731 against BioCLIP-2's 0.874 at class (1.2x) to 0.269 against 0.544 at scientific name (2x). On trait size measurement, 15 of the 18 models do no better than an image-blind baseline that predicts one fixed number for every specimen, and on re-identification, 17 of the 18 models fall below chance under adversarial conditions. These failures persist across a tenfold range of model size. We hope Bio-VQA becomes a standard test of how well VLM capabilities transfer to the biological domain.
Apr 4, 2026

MG2^2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) mitigates hallucinations in Multimodal Large Language Models (MLLMs), yet existing systems struggle with complex cross-modal reasoning. Flat vector retrieval often ignores structural dependencies, while current graph-based methods rely on costly ``translation-to-text'' pipelines that discard fine-grained visual information. To address these limitations, we propose \textbf{MG2^2-RAG}, a lightweight Multi-Granularity Graph RAG framework that jointly improves graph construction, modality fusion, and cross-modal retrieval. MG2^2-RAG constructs a hierarchical multimodal knowledge graph by combining lightweight textual parsing with entity-driven visual grounding, enabling textual entities and visual regions to be fused into unified multimodal nodes that preserve atomic evidence. Building on this representation, we introduce a multi-granularity graph retrieval mechanism that aggregates dense similarities and propagates relevance across the graph to support structured multi-hop reasoning. Extensive experiments across four representative multimodal tasks (i.e., retrieval, knowledge-based VQA, reasoning, and classification) demonstrate that MG2^2-RAG consistently achieves state-of-the-art performance while reducing graph construction overhead with an average 43.3×\times speedup and 23.9×\times cost reduction compared with advanced graph-based frameworks.