发表机构
University of Twente; Busitema University（特文特大学; 布西特马大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出MLD统一基准并采用层次化模型HiLeaD，跨区域测试显示域差距显著，池化数据与层次结构带来稳定提升，表明数据多样性比模型设计更关键。
AI 中文摘要
用于作物叶片病害识别的深度学习模型通常报告接近完美的准确率，但往往是在受控实验室条件下收集的单一数据集上训练和评估的，导致其在现实跨区域域偏移下的行为鲜为人知。我们引入了MLD（多作物叶片病害）数据集，这是一个统一的多区域基准，将来自美国、亚洲和非洲的六个公开作物病害数据集合并为一个共享的层次化分类体系，涵盖18种作物、56个作物病害类别（每种作物包括一个健康类别），共计167,427张图像。我们定义了标准化的单源和多源池化评估协议，明确探测跨区域泛化能力。我们还研究了通过层次化公式（HiLeaD）利用固有的作物-病害依赖关系，即根据预测的作物来条件化病害预测，是否能改善跨区域偏移下的识别性能。在HiLeaD下，在PlantVillage上训练的模型在域内病害F1分数达到99.07%，但在PlantDoc上测试时骤降至12.88%，暴露了严重的跨区域域差距。在池化的MLD数据集上训练的模型部分恢复了跨区域病害F1分数，在PlantDoc上从12.88%提升到39.64%（HiLeaD），实现了26.76个百分点的改进。层次化公式提供了一致的额外增益，在MLD数据集下，与平坦基线相比，病害F1分数提高了1.71到4.88个百分点，表明该领域的进展目前更多受限于数据覆盖和多样性，而非模型设计。
英文摘要
Deep learning models for crop leaf disease recognition routinely report near-perfect accuracy yet are typically trained and evaluated on a single dataset collected under controlled laboratory conditions, leaving their behavior under realistic cross-region domain shift poorly understood. We introduce MLD (Multi-crop Leaf Disease) dataset, a unified multi-region benchmark that combines six public crop-disease datasets from the USA, Asia, and Africa into a shared hierarchical taxonomy spanning 18 crops, 56 crop-disease classes (including one healthy class per crop) making 167,427 images. We define standardized single-source and pooled multi-source evaluation protocols that explicitly probe cross-region generalization. We also investigate whether exploiting the inherent crop-to-disease dependency via a hierarchical formulation (HiLeaD) that conditions disease prediction on the predicted crop improves recognition under cross-region shift. Under the HiLeaD, the model trained on PlantVillage achieves 99.07% in-domain disease F1 but collapses to 12.88% when tested on PlantDoc, exposing a severe cross-region domain gap. The model trained on the pooled MLD dataset partly recovers cross-region disease F1 from 12.88% to 39.64% on PlantDoc (HiLeaD), achieving a 26.76 percentage point improvement. The hierarchical formulation provides a consistent additional gain, ranging from 1.71 to 4.88 percentage points in disease F1 over the flat baseline under the MLD dataset indicating that progress in this area is currently limited more by data coverage and diversity than by model design.
