Wang Jianlong, Qin Congcong, Hou Beibei, Yuan Yuan, Zhang Yake, Feng Wenfeng
School of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, China.
School of Education, Henan Normal University, Xinxiang, China.
Front Plant Sci. 2024 Oct 31;15:1398277. doi: 10.3389/fpls.2024.1398277. eCollection 2024.
In response to the current mainstream deep learning detection methods with a large number of learned parameters and the complexity of apple leaf disease scenarios, the paper proposes a lightweight method and names it LCGSC-YOLO. This method is based on the LCNet(A Lightweight CPU Convolutional Neural Network) and GSConv(Group Shuffle Convolution) module modified YOLO(You Only Look Once) framework.
Firstly, the lightweight LCNet is utilized to reconstruct the backbone network, with the purpose of reducing the number of parameters and computations of the model. Secondly, the GSConv module and the VOVGSCSP (Slim-neck by GSConv) module are introduced in the neck network, which makes it possible to minimize the number of model parameters and computations while guaranteeing the fusion capability among the different feature layers. Finally, coordinate attention is embedded in the tail of the backbone and after each VOVGSCSP module to improve the problem of detection accuracy degradation issue caused by model lightweighting.
The experimental results show the LCGSC-YOLO can achieve an excellent detection performance with mean average precision of 95.5% and detection speed of 53 frames per second (FPS) on the mixed datasets of Plant Pathology 2021 (FGVC8) and AppleLeaf9.
The number of parameters and Floating Point Operations (FLOPs) of the LCGSC-YOLO are much less thanother related comparative experimental algorithms.
针对当前主流深度学习检测方法存在大量学习参数以及苹果叶病害场景复杂的问题，本文提出了一种轻量级方法并将其命名为LCGSC - YOLO。该方法基于LCNet（一种轻量级CPU卷积神经网络）和GSConv（组混洗卷积）模块对YOLO（You Only Look Once）框架进行改进。
首先，利用轻量级的LCNet重构骨干网络，以减少模型的参数数量和计算量。其次，在颈部网络中引入GSConv模块和VOVGSCSP（通过GSConv实现的细颈结构）模块，这使得在保证不同特征层之间融合能力的同时，能够最大限度地减少模型参数数量和计算量。最后，在骨干网络尾部以及每个VOVGSCSP模块之后嵌入坐标注意力，以改善因模型轻量化导致的检测精度下降问题。
实验结果表明，LCGSC - YOLO在植物病理学2021（FGVC8）和AppleLeaf9的混合数据集上能够实现出色的检测性能，平均精度均值达到95.5%，检测速度为每秒53帧（FPS）。
LCGSC - YOLO的参数数量和浮点运算次数（FLOPs）远少于其他相关对比实验算法。
