AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning

• URL: http://arxiv.org/abs/2604.17889v1
• Date: Mon, 20 Apr 2026 07:02:10 GMT
• Title: AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning
• Abstract summary: We propose AeroRAG, a scene-graph-guided multimodal retrieval-augmented generation framework for visual question answering.<n>The framework first converts an input image into structured visual knowledge, including object categories, quantities, and semantic relations.<n>It then retrieves query-relevant semantic chunks to construct compact prompts for a text-based large language model.
• Score: 2.9055098900305634
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite recent progress in multimodal large language models (MLLMs), reliable visual question answering in aerial scenes remains challenging. In such scenes, task-critical evidence is often carried by small objects, explicit quantities, coarse locations, and inter-object relations, whereas conventional dense visual-token representations are not well aligned with these structured semantics. To address this interface mismatch, we propose AeroRAG, a scene-graph-guided multimodal retrieval-augmented generation framework for visual question answering. The framework first converts an input image into structured visual knowledge, including object categories, quantities, spatial locations, and semantic relations, and then retrieves query-relevant semantic chunks to construct compact prompts for a text-based large language model. Rather than relying on direct reasoning over dense visual tokens, our method introduces a more explicit intermediate interface between perception and language reasoning. Experiments on the AUG aerial dataset and the general-domain VG-150 benchmark show consistent improvements over six strong MLLM baselines, with the largest gains observed in dense aerial scenes and relation-sensitive reasoning. We further evaluate the framework on VQAv2 to verify that the proposed interface remains compatible with standard visual reasoning settings. These results suggest that structured retrieval is a practical design direction for deployment-oriented and grounded visual reasoning systems.

Related papers

• See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding [41.70825455674463]
  SWIM (See What I Mean) is a training strategy that aligns vision and language representations to enable fine-grained object understanding solely from textual prompts.<n>We show that SWIM substantially improves text-visual alignment and achieves superior performance over visual-prompt-based methods on fine-grained object understanding benchmarks.
  arXiv  Detail & Related papers  (2026-05-18T08:09:37Z)
• GaLa: Hypergraph-Guided Visual Language Models for Procedural Planning [14.265218749993956]
  Implicit spatial relations and deep semantic structures encoded in object attributes are crucial for procedural planning in embodied AI systems.<n>We propose GaLa, a vision language framework for multimodal procedural planning.<n>We show that GaLa significantly outperforms existing methods in terms of execution success rate, LCS, and planning correctness.
  arXiv  Detail & Related papers  (2026-04-19T04:04:02Z)
• Perception-Aware Multimodal Spatial Reasoning from Monocular Images [57.42071289037214]
  spatial reasoning from monocular images is essential for autonomous driving.<n>Current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception.<n>We propose a perception-aware multimodal reasoning framework that equipsVLMs with explicit object-centric grounding ability.
  arXiv  Detail & Related papers  (2026-03-07T02:05:12Z)
• A Multimodal Depth-Aware Method For Embodied Reference Understanding [56.30142869506262]
  Embodied Reference Understanding requires identifying a target object in a visual scene based on both language instructions and pointing cues.<n>We propose a novel ERU framework that jointly leverages data augmentation, depth-map modality, and a depth-aware decision module.
  arXiv  Detail & Related papers  (2025-10-09T14:32:21Z)
• Towards Text-Image Interleaved Retrieval [49.96332254241075]
  We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences.<n>We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries.<n>We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
  arXiv  Detail & Related papers  (2025-02-18T12:00:47Z)
• Enhanced Multimodal RAG-LLM for Accurate Visual Question Answering [10.505845766495128]
  Multimodal large language models (MLLMs) have made significant progress in integrating visual and textual modalities.<n>We propose a novel framework based on multimodal retrieval-augmented generation (RAG)<n>RAG introduces structured scene graphs to enhance object recognition, relationship identification, and spatial understanding within images.
  arXiv  Detail & Related papers  (2024-12-30T13:16:08Z)
• EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models [80.00303150568696]
  We propose a novel Multimodal Large Language Models (MLLM) that empowers comprehension of arbitrary referring visual prompts with less training efforts than existing approaches. Our approach embeds referring visual prompts as spatial concepts conveying specific spatial areas comprehensible to the MLLM. We also propose a Geometry-Agnostic Learning paradigm (GAL) to further disentangle the MLLM's region-level comprehension with the specific formats of referring visual prompts.
  arXiv  Detail & Related papers  (2024-09-25T08:22:00Z)
• Open-Vocabulary Camouflaged Object Segmentation [66.94945066779988]
  We introduce a new task, open-vocabulary camouflaged object segmentation (OVCOS) We construct a large-scale complex scene dataset (textbfOVCamo) containing 11,483 hand-selected images with fine annotations and corresponding object classes. By integrating the guidance of class semantic knowledge and the supplement of visual structure cues from the edge and depth information, the proposed method can efficiently capture camouflaged objects.
  arXiv  Detail & Related papers  (2023-11-19T06:00:39Z)
• ORD: Object Relationship Discovery for Visual Dialogue Generation [60.471670447176656]
  We propose an object relationship discovery (ORD) framework to preserve the object interactions for visual dialogue generation. A hierarchical graph convolutional network (HierGCN) is proposed to retain the object nodes and neighbour relationships locally, and then refines the object-object connections globally. Experiments have proved that the proposed method can significantly improve the quality of dialogue by utilising the contextual information of visual relationships.
  arXiv  Detail & Related papers  (2020-06-15T12:25:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.