发表机构
Cornell University; University of the Peloponnese; Agricultural University of Athens（康奈尔大学; 伯罗奔尼撒大学; 雅典农业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出H²MAF框架，结合EfficientNet-B3、ConvNeXt-Tiny与Gemma、Qwen等MLLM，在PlantDoc及Cornell机器人田间数据集上实现高准确率可解释植物病害诊断，验证了MLLM仲裁的应用潜力。
AI 中文摘要
准确的田间植物病害诊断需要可靠融合不确定且冲突的感知证据。我们提出混合分层多智能体框架（H²MAF），结合EfficientNet-B3与ConvNeXt-Tiny的决策级融合，以及开源权重多模态大语言模型（MLLM）Gemma 4 E4B和Qwen3.5 4B的语义仲裁，利用结构化JSON证据生成可解释诊断结果、风险等级、治疗紧迫性及经济损失。H²MAF在PlantDoc（2922张图像，27类）及两个非公开、由Cornell机器人持续采集的田间数据集（Stage 2：20GB，4215张图像；Stage 4：40GB，7227张图像）的14364张图像（1370张测试图像）上进行评估，涵盖未受控田间条件下的早疫病、晚疫病和Septoria叶斑病。在PlantDoc上，Gemma将准确率从63.9%提升至68.5%，在CNN冲突子集（占比41.7%）上提升7.6个百分点；Cornell数据集上的准确率分别达99.3%和98.9%，分歧仅为1.7%-4.1%，证明MLLM效用依赖于冲突程度。Gemma的临界风险误差为0.14-0.5个百分点，而Qwen的过度标记误差为3.5-14.4个百分点。这些结果表明，MLLM仲裁是一种有前景但需校准的可解释农业AI及机器人现场决策支持方法。
英文摘要
Accurate field plant disease diagnosis requires reliable fusion of uncertain and conflicting perceptual evidence. We present the Hybrid Hierarchical Multi-Agent Framework (H$^{2}$MAF), combining decision-level fusion of EfficientNet-B3 and ConvNeXt-Tiny with semantic arbitration by open-weight multimodal large language models (MLLMs), Gemma 4 E4B and Qwen3.5 4B, using structured JSON evidence to generate explainable diagnoses, risk levels, treatment urgency, and financial exposure. (H$^{2}$MAF) is evaluated on 14,364 images (1,370 test images) across PlantDoc (2,922 images, 27 classes) and two non-public, continuously captured Cornell robot-acquired field datasets: Stage 2 (20 GB; 4,215 images) and Stage 4 (40 GB; 7,227 images), covering Early Blight, Late Blight, and Septoria Leaf Spot under uncontrolled field conditions. On PlantDoc, Gemma improves accuracy from 63.9% to 68.5%, achieving +7.6 points on the 41.7% CNN-conflict subset. Cornell accuracies reach 99.3% and 98.9%, with only 1.7-4.1% disagreement, demonstrating conflict-dependent MLLM utility. The critical-risk error of gemma is 0.14-0.5 points, whereas Qwen overflags by 3.5-14.4 points. These results establish MLLM arbitration as a promising, yet calibration-dependent, approach for explainable agricultural AI and robotic field decision support. Github Link: https://github.com/Applied-AI-Research-Lab/Explainable-AI-Plant-Disease-Detection
