Hai Tong, Shao Yuxin, Zhang Xiyan, Yuan Guangqi, Jia Ruihao, Fu Zhengjie, Wu Xiaohan, Ge Xinjin, Song Yihong, Dong Min, Yan Shuo
China Agricultural University, Beijing 100083, China.
School of English and International Studies, Beijing Foreign Studies University, Beijing 100193, China.
Plants (Basel). 2025 Mar 1;14(5):760. doi: 10.3390/plants14050760.
This study proposes a model for leafy vegetable disease detection and segmentation based on a few-shot learning framework and a prototype attention mechanism, with the aim of addressing the challenges of complex backgrounds and few-shot problems. Experimental results show that the proposed method performs excellently in both object detection and semantic segmentation tasks. In the object detection task, the model achieves a precision of 0.93, recall of 0.90, accuracy of 0.91, mAP@50 of 0.91, and mAP@75 of 0.90. In the semantic segmentation task, the precision is 0.95, recall is 0.92, accuracy is 0.93, mAP@50 is 0.92, and mAP@75 is 0.92. These results show that the proposed method significantly outperforms the traditional methods, such as YOLOv10 and TinySegformer, validating the advantages of the prototype attention mechanism in enhancing model robustness and fine-grained feature expression. Furthermore, the prototype loss function, which optimizes the distance relationship between samples and category prototypes, significantly improves the model's ability to discriminate between categories. The proposed method shows great potential in agricultural disease detection, particularly in scenarios with few samples and complex backgrounds, offering broad application prospects.
本研究提出了一种基于少样本学习框架和原型注意力机制的叶菜类蔬菜病害检测与分割模型，旨在解决复杂背景和少样本问题带来的挑战。实验结果表明，所提方法在目标检测和语义分割任务中均表现出色。在目标检测任务中，该模型的精度为0.93，召回率为0.90，准确率为0.91，mAP@50为0.91，mAP@75为0.90。在语义分割任务中，精度为0.95，召回率为0.92，准确率为0.93，mAP@50为0.92，mAP@75为0.92。这些结果表明，所提方法显著优于传统方法，如YOLOv10和TinySegformer，验证了原型注意力机制在增强模型鲁棒性和细粒度特征表达方面的优势。此外，优化样本与类别原型之间距离关系的原型损失函数显著提高了模型的类别区分能力。所提方法在农业病害检测中显示出巨大潜力，特别是在样本少和背景复杂的场景中，具有广阔的应用前景。
