arXiv cs.AI· Jiarui Zhang, Junqi Hu, Zurong Mai, Yang Liu, Yuhang Chen, Shuohong Lou, Henglian Huang, Hong Cheng, Lingyuan Zhao, Jianxi Huang, Yutong Lu, Haohuan Fu, Juepeng Zheng·· 3 小时前AI 评分37
AgroOmni：面向跨尺度多模态推理的大规模多视角农业数据集
AgroOmni: A Large-Scale Multi-view Agricultural Dataset for Cross-Scale Multimodal Reasoning
AI 导读
研究团队发布 AgroOmni 大规模多视角农业训练语料，包含 268,119 个视觉问答对，覆盖 14 种任务类型的 56 个专业任务类别，解决现有 MLLM 因地面视角偏差导致的尺度混淆问题。
正文 · 原文
Authors:Jiarui Zhang, Junqi Hu, Zurong Mai, Yang Liu, Yuhang Chen, Shuohong Lou, Henglian Huang, Hong Cheng, Lingyuan Zhao, Jianxi Huang, Yutong Lu, Haohuan Fu, Juepeng Zheng
Abstract:Modern agricultural data is sourced from diverse platforms and spans multiple spatial scales, ranging from ground-level close-up photography to Unmanned Aerial Vehicle (UAV) aerial observation and satellite remote sensing imagery. Accordingly, agricultural multimodal reasoning demands robust cross-scale spatial understanding. However, due to the lack of multi-view agricultural benchmark datasets, existing multimodal large language models (MLLMs) exhibit severe ground-level bias, which leads to scale confusion then semantic collapse in agricultural perception tasks, such as misinterpreting farmland imagery as walls or floors. To address this, we introduce AgroOmni, a large-scale multi-view training corpus with 268,119 Visual Question Answering pairs covering 56 specialized task categories across 14 task types, designed to capture diverse scales in modern precision this http URL on this dataset, we propose AgroNVILA, which achieves a new state-of-the-art of 59.86% on the AgroMind benchmark (+12.57 over GPT-5.2), effectively mitigating the multi-view cross-scale gap for holistic agricultural understanding. Diagnostic evaluations on AgMMU further reveal an inherent heterogeneity between macro-priors and micro-diagnostics through constrained zero-shot performance. Meanwhile, even minimal fine-tuning leads to a dramatic performance gain of AgroNVILA on AgMMU, strongly demonstrating its generalization capability empowered by AgroOmni. Full training scripts are publicly available at this https URL, and the AgroOmni dataset is released at this https URL.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.14342 [cs.CV] |
| (or arXiv:2603.14342v3 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2603.14342 arXiv-issued DOI via DataCite |
Submission history
From: Jiarui Zhang [view email]
[v1]
Sun, 15 Mar 2026 12:24:03 UTC (7,595 KB)
[v2]
Mon, 8 Jun 2026 12:43:48 UTC (6,042 KB)
[v3]
Thu, 12 Nov 2026 12:37:25 UTC (6,785 KB)
来源：arXiv cs.AI · arxiv.org