高级检索
    赵法川, 徐晓辉, 宋涛, 等. 融合多头注意力的轻量级作物病虫害识别[J]. 华南农业大学学报, 2023, 44(6): 986-994. doi: 10.7671/j.issn.1001-411X.202208051
    引用本文: 赵法川, 徐晓辉, 宋涛, 等. 融合多头注意力的轻量级作物病虫害识别[J]. 华南农业大学学报, 2023, 44(6): 986-994. doi: 10.7671/j.issn.1001-411X.202208051
    shu
    ZHAO Fachuan, XU Xiaohui, SONG Tao, et al. A lightweight crop pest identification method based on multi-head attention[J]. Journal of South China Agricultural University, 2023, 44(6): 986-994. doi: 10.7671/j.issn.1001-411X.202208051
    Citation: ZHAO Fachuan, XU Xiaohui, SONG Tao, et al. A lightweight crop pest identification method based on multi-head attention[J]. Journal of South China Agricultural University, 2023, 44(6): 986-994. doi: 10.7671/j.issn.1001-411X.202208051
    shu

    融合多头注意力的轻量级作物病虫害识别

    A lightweight crop pest identification method based on multi-head attention

      摘要
    • 摘要:
      目的 解决当前病虫害识别方法参数多、计算量大、难以在边缘嵌入式设备部署的问题，实现农作物病虫害精准识别，提高农作物产量和品质。
      方法 提出一种融合多头注意力的轻量级卷积网络(Multi-head attention to convolutional neural network，M2CNet)。M2CNet采用层级金字塔结构，首先，结合深度可分离残差和循环全连接残差构建局部捕获块，用来捕捉短距离信息；其次，结合全局子采样注意力和轻量级前馈网络构建轻量级全局捕获块，用来捕捉长距离信息。提出M2CNet-S/B/L 3个变体以满足不同的边缘部署需求。
      结果 M2CNet-S/B/L参数量分别为1.8M、3.5M和5.8M，计算量(Floating point operations，FLOPs)分别为0.23G、0.39G和0.60G。M2CNet-S/B/L对PlantVillage病害数据集取得了大于99.7%的Top5准确率和大于95.9%的Top1准确率，对IP102虫害数据集取得了大于88.4%的Top5准确率和大于67.0%的Top1准确率，且比同级别的模型表现优异。
      结论 该方法能够对作物病虫害进行有效识别，且可为边缘侧工程部署提供有益参考。

       

      Abstract:
      Objective To solve the problems that the current pest identification method has many parameters, a large amount of calculation and is difficult to deploy embedded devices at the edge, so as to realize accurate identification of crop pests and diseases, and improve crop yield and quality.
      Method A lightweight convolutional neural network called multi-head attention to convolutional neural network (M2CNet) was proposed. M2CNet adopted hierarchical pyramid structure. Firstly, a local capture block was constructed by combining depth separable residual and cyclic fully connected residual to capture short-range information. Secondly, a lightweight global capture block was constructed by combining global subsampling attention and lightweight feedforward network to capture long-distance information. Three variants, namely M2CNet-S, M2CNet-B, and M2CNet-L, were proposed by M2CNet to meet different edge deployment requirements.
      Result M2CNet-S/B/L had parameter sizes of 1.8M, 3.5M and 5.8M, and floating point operations of 0.23G, 0.39G, and 0.60G, respectively. M2CNet-S/B/L achieved top5 accuracy greater than 99.7% and top1 accuracy greater than 95.9% in PlantVillage disease dataset, and top5 accuracy greater than 88.4% and top1 accuracy greater than 67.0% in IP102 pest dataset, outperforming models of the same level in comparison.
      Conclusion Effective identification of crop diseases and pests can be achieved by this method, and it provides valuable references for edge engineering deployment.

       

      • HTML全文
      • 参考文献(31)
      • 相关文章
      • 施引文献
    • 资源附件(0)

    /

    返回文章
    返回