数字农科院2.0

EMSAM: enhanced multi-scale segment anything model for leaf disease segmentation

文献类型： 外文期刊

作者： Junlong Li;Quan Feng;Jianhua Zhang;Sen Yang

作者机构：

关键词： adapter tuning;leaf disease segmentation;multi-task learning;parameter efficient fine-tuning;segment anything model

期刊名称： Frontiers in Plant Science

ISSN： 1664-462X

年卷期： 2025 年 16 卷

页码：

收录情况： SCIE（2025版）

摘要： Accurate segmentation of leaf diseases is crucial for crop health management and disease prevention. However, existing studies fall short in addressing issues such as blurred disease spot boundaries and complex feature distributions in disease images. Although the vision foundation model, Segment Anything Model (SAM), performs well in general segmentation tasks within natural scenes, it does not exhibit good performance in plant disease segmentation. To achieve fine-grained segmentation of leaf disease images, this study proposes an advanced model: Enhanced Multi-Scale SAM (EMSAM). EMSAM employs the Local Feature Extraction Module (LFEM) and the Global Feature Extraction Module (GFEM) to extract local and global features from images respectively. The LFEM utilizes multiple convolutional layers to capture lesion boundaries and detailed characteristics, while the GFEM fine-tunes ViT blocks using a Multi-Scale Adaptive Adapter (MAA) to obtain multi-scale global information. Both outputs of LFEM and GFEM are then effectively fused in the Feature Fusion Module (FFM), which is optimized with cross-branch and channel attention mechanisms, significantly enhancing the model’s ability to handle blurred boundaries and complex shapes. EMSAM integrates lightweight linear layers as classification heads and employs a joint loss function for both classification and segmentation tasks. Experimental results on the PlantVillage dataset demonstrate that EMSAM outperforms the second-best state-of-the-art semantic segmentation model by 2.45% in Dice Coefficient and 6.91% in IoU score, and surpasses the baseline method by 21.40% and 22.57%, respectively. Particularly, for images with moderate and severe disease levels, EMSAM achieved Dice Coefficients of 0.8354 and 0.8178, respectively, significantly outperforming other semantic segmentation algorithms. Additionally, the model achieved a classification accuracy of 87.86% across the entire dataset, highlighting EMSAM’s effectiveness and superiority in plant disease segmentation and classification tasks.

分类号：

  • 相关文献

[1]Achieving precise cropland parcel extraction from remote sensing images through integration of segment anything model and adaptive mask refinement. Li, Huibin,Zhu, Jianyu,Mao, Xing,Hao, Xueli,Li, Shiyao,Yu, Qiangyi,Shi, Yun,Qian, Jianping. 2025

[2]MtCro: multi-task deep learning framework improves multi-trait genomic prediction of crops. Chao, Dian,Wang, Hao,Wan, Fengqiang,Yan, Shen,Fang, Wei,Yang, Yang. 2025

[3]Soybean yield estimation and lodging discrimination based on lightweight UAV and point cloud deep learning. Longyu Zhou,Dezhi Han,Guangyao Sun,Yaling Liu,Xiaofei Yan,Hongchang Jia,Long Yan,Puyu Feng,Yinghui Li,Lijuan Qiu,Yuntao Ma. 2025

[4]A novel cross-modal decoupling dual-spectral fusion system and method: A case study on the on-site estimation of fresh tobacco leaf curing characteristics. Zhongtao Huang,Shichang Wang,Rongguang Zhu,Yapeng Kang,Lingfeng Meng,Jie Ren. 2025

作者其他论文 更多>>