宁夏大学学报（自然科学版中英文）2026，Vol.47Issue(1)：42-49,8.DOI:10.20176/j.cnki.nxdz.000044
迁移MobileNetV3的玉米病害识别方法
Transferred MobileNetV3 Method for Corn Disease Recognition
摘要
Abstract
A method of corn disease recognition based on transfer learning using MobilenetV3 is proposed.The training dataset is augmented through online data enhancement,and the learning results of the MobilenetV3-Small network on the ImageNet dataset are utilized as pre-trained weights to construct the transfer learning model.A deep separable convolution module is adopted to reduce the model's parameters count.Additionally,a channel attention mechanism and the H-Swish activation function are incorporated to enhance both the accu-racy and efficiency of the model's recognition capabilities.The Adam optimizer and cross-entropy loss function are used to train the top-level classifier after migration.Experimental results show that the model achieves an accuracy of 95.68%on the test set.Subsequently,the last one-third of layers in the transfer model are unfro-zen,and the model is well tuned by adjusting the learning rate and optimizer parameters,resulting in a final test accuracy of 98.15%,which is an improvement of 2.47%compared to the pre-tuning accuracy.关键词
迁移学习/微调/MobileNetV3/卷积神经网络/玉米病害Key words
transfer learning/fine tuning/MobileNetV3/convolutional neural network/corn diseases分类
信息技术与安全科学引用本文复制引用
史宝明,贺元香,赵霞..迁移MobileNetV3的玉米病害识别方法[J].宁夏大学学报（自然科学版中英文）,2026,47(1):42-49,8.基金项目
甘肃省教育厅创新基金资助项目(2023A-181) （2023A-181）
国家自然科学基金资助项目(61841203) （61841203）
