基于MA-ConvNext网络和分步关系知识蒸馏的苹果叶片病害识别
Identification of apple leaf diseases based on MA-ConvNext network and stepwise relational knowledge distillation
刘欢 1李云红 1张蕾涛 1郭越 2苏雪平 1朱耀麟 1侯乐乐1
作者信息
- 1. 西安工程大学电子信息学院,陕西西安 710048
- 2. 山西大学生命科学学院,山西太原 030031
- 折叠
摘要
针对复杂环境下苹果叶片病害图像背景杂乱、病斑大小不一,以及现有模型参数多、计算量大的问题,提出基于注意力和多尺度特征融合的苹果叶片病害识别网络(MA-ConvNext).通过引入多尺度空间通道重组块(MSCB)和融合三分支注意力机制的特征提取模块(TAFB),有效提取苹果叶片病害图像不同尺度的特征,增强模型对叶片病斑的关注.采用分步关系知识蒸馏方法,将"教师"网络(MA-ConvNext)和"中间"网络(DenseNet121)融合,指导"学生"网络(EfficientNet-B0)训练,实现模型轻量化.实验结果表明,MA-ConvNext网络识别准确率为99.38%,较ResNet50、MobileNet-V3 和EfficientNet-V2 网络分别提高了 3.98 个百分点、7.55 个百分点和 4.27 个百分点.经过分步关系知识蒸馏后,识别准确率较蒸馏前提高了 1.76 个百分点,并且具有更小的网络规模和参数量,分别为 1.56×107、5.29×106.所提方法能为后续精准农业的病虫害检测提供新思路和技术支持.
Abstract
The backgrounds are cluttered,the spot sizes of apple leaf disease are varying in complex environments,and the existing models have the problems of multiple parameters and a large amount of calculation.Thus,an apple leaf disease recognition network,ConvNext network based on attention and multiscale feature fusion(MA-ConvNext),was proposed.A multiscale spatial reconstruction and channel reconstruction block(MSCB)and a feature extraction block with triplet attention fusion(TAFB)were utilized to effectively extract the features at different scales and enhance the focus on leaf disease spots.Additionally,a stepwise relational knowledge distillation method was employed to fuse the"teacher"network(MA-ConvNext)with an"intermediate"network(DenseNet121)to guide the training of the"student"network(EfficientNet-B0)and achieve the model lightweighting.Experimental results showed that MA-ConvNext achieved a recognition accuracy of 99.38%,improving by 3.98 percentage points,7.55 percentage points and 4.27 percentage points compared to ResNet50,MobileNet-V3,and EfficientNet-V2 networks,respectively.After the stepwise relational knowledge distillation,the recognition accuracy further improved by 1.76 percentage points,with a smaller network size and parameters of 1.56×107 and 5.29×106.respectively.The proposed method offers new insights and technical support for the precise detection of pests and diseases in agriculture.
关键词
苹果叶片病害识别/注意力/多尺度特征融合/分步关系/知识蒸馏Key words
apple leaf disease identification/attention/multiscale feature fusion/stepwise relationship/know-ledge distillation引用本文复制引用
基金项目
国家自然科学基金资助项目(62203344)
陕西省自然科学基础研究重点资助项目(2022JZ-35)
陕西高校青年创新团队资助项目()
出版年
2024
NETL
NSTL
万方数据