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·· 1 天前AI 评分29
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 大规模多视角农业数据集，含 268,119 个视觉问答对，覆盖 14 种任务类型下的 56 个专业任务类别。基于该数据集提出的 AgroNVILA 在 AgroMind 基准上达到 59.86% 的 SOTA，较 GPT-5.2 高出 12.57 个百分点，缓解了多视角跨尺度理解差距。训练脚本与数据集均已公开。
正文 · AI 翻译
译文尚不完整，完整内容请切换到原文。
作者：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.
| 学科： | 计算机视觉与模式识别（cs.CV）；人工智能（cs.AI） |
| 引用格式： | arXiv:2603.14342 [cs.CV] |
| （或本版本使用 arXiv:2603.14342v3 [cs.CV]） | |
| https://doi.org/10.48550/arXiv.2603.14342 arXiv 颁发的 DOI 通过 DataCite |
提交历史
来自：Jiarui Zhang [查看邮箱]
[v1]
2026年3月15日周日 12:24:03 UTC（7,595 KB）
[v2]
2026年6月8日周一 12:43:48 UTC（6,042 KB）
[v3]
2026年11月12日周四 12:37:25 UTC（6,785 KB）
来源：arXiv cs.AI · arxiv.org