Distilled-MobileNet Model of Convolutional Neural Network Simplified Structure for Plant Disease Recognition
The development of convolutional neural networks(CNN) has brought a large number of network parameters and huge model volumes, which greatly limites the application on devices with small computing resources, such as single-chip microcomputers and mobile devices. In order to solve the problem, a stru...
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN ZH |
| Publicado: |
Editorial Office of Smart Agriculture
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/f84d60be63634dc9b10de6e32d98663f |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:f84d60be63634dc9b10de6e32d98663f |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:f84d60be63634dc9b10de6e32d98663f2021-11-17T07:52:00ZDistilled-MobileNet Model of Convolutional Neural Network Simplified Structure for Plant Disease Recognition2096-809410.12133/j.smartag.2021.3.1.202009-SA004https://doaj.org/article/f84d60be63634dc9b10de6e32d98663f2021-03-01T00:00:00Zhttp://www.smartag.net.cn/article/2021/2096-8094/2096-8094-2021-3-1-109.shtmlhttps://doaj.org/toc/2096-8094The development of convolutional neural networks(CNN) has brought a large number of network parameters and huge model volumes, which greatly limites the application on devices with small computing resources, such as single-chip microcomputers and mobile devices. In order to solve the problem, a structured model compression method was studied in this research. Its core idea was using knowledge distillation to transfer the knowledge from the complex integrated model to a lightweight small-scale neural network. Firstly, VGG16 was used to train a teacher model with a higher recognition rate, whose volume was much larger than the student model. Then the knowledge in the model was transfered to MobileNet by using distillation. The parameters number of the VGG16 model was greatly reduced. The knowledge-distilled model was named Distilled-MobileNet, and was applied to the classification task of 38 common diseases (powdery mildew, Huanglong disease, etc.) of 14 crops (soybean, cucumber, tomato, etc.). The performance test of knowledge distillation on four different network structures of VGG16, AlexNet, GoogleNet, and ResNet showed that when VGG16 was used as a teacher model, the accuracy of the model was improved to 97.54%. Using single disease recognition rate, average accuracy rate, model memory and average recognition time as 4 indicators to evaluate the accuracy of the trained Distilled-MobileNet model in a real environment, the results showed that, the average accuracy of the model reached 97.62%, and the average recognition time was shortened to 0.218 s, only accounts for 13.20% of the VGG16 model, and the model size was reduced to only 19.83 MB, which was 93.60% smaller than VGG16. Compared with traditional neural networks, distilled-mobile model has a significant improvement in reducing size and shorting recognition time, and can provide a new idea for disease recognition on devices with limited memory and computing resources.QIU WenjieYE JinHU LiangqingYANG JuanLI QiliMO JianyouYI WanmaoEditorial Office of Smart Agriculturearticledisease identificationdeep learningmodel compressionknowledge distillationconvolutional neural networkAgriculture (General)S1-972Technology (General)T1-995ENZH智慧农业, Vol 3, Iss 1, Pp 109-117 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN ZH |
| topic |
disease identification deep learning model compression knowledge distillation convolutional neural network Agriculture (General) S1-972 Technology (General) T1-995 |
| spellingShingle |
disease identification deep learning model compression knowledge distillation convolutional neural network Agriculture (General) S1-972 Technology (General) T1-995 QIU Wenjie YE Jin HU Liangqing YANG Juan LI Qili MO Jianyou YI Wanmao Distilled-MobileNet Model of Convolutional Neural Network Simplified Structure for Plant Disease Recognition |
| description |
The development of convolutional neural networks(CNN) has brought a large number of network parameters and huge model volumes, which greatly limites the application on devices with small computing resources, such as single-chip microcomputers and mobile devices. In order to solve the problem, a structured model compression method was studied in this research. Its core idea was using knowledge distillation to transfer the knowledge from the complex integrated model to a lightweight small-scale neural network. Firstly, VGG16 was used to train a teacher model with a higher recognition rate, whose volume was much larger than the student model. Then the knowledge in the model was transfered to MobileNet by using distillation. The parameters number of the VGG16 model was greatly reduced. The knowledge-distilled model was named Distilled-MobileNet, and was applied to the classification task of 38 common diseases (powdery mildew, Huanglong disease, etc.) of 14 crops (soybean, cucumber, tomato, etc.). The performance test of knowledge distillation on four different network structures of VGG16, AlexNet, GoogleNet, and ResNet showed that when VGG16 was used as a teacher model, the accuracy of the model was improved to 97.54%. Using single disease recognition rate, average accuracy rate, model memory and average recognition time as 4 indicators to evaluate the accuracy of the trained Distilled-MobileNet model in a real environment, the results showed that, the average accuracy of the model reached 97.62%, and the average recognition time was shortened to 0.218 s, only accounts for 13.20% of the VGG16 model, and the model size was reduced to only 19.83 MB, which was 93.60% smaller than VGG16. Compared with traditional neural networks, distilled-mobile model has a significant improvement in reducing size and shorting recognition time, and can provide a new idea for disease recognition on devices with limited memory and computing resources. |
| format |
article |
| author |
QIU Wenjie YE Jin HU Liangqing YANG Juan LI Qili MO Jianyou YI Wanmao |
| author_facet |
QIU Wenjie YE Jin HU Liangqing YANG Juan LI Qili MO Jianyou YI Wanmao |
| author_sort |
QIU Wenjie |
| title |
Distilled-MobileNet Model of Convolutional Neural Network Simplified Structure for Plant Disease Recognition |
| title_short |
Distilled-MobileNet Model of Convolutional Neural Network Simplified Structure for Plant Disease Recognition |
| title_full |
Distilled-MobileNet Model of Convolutional Neural Network Simplified Structure for Plant Disease Recognition |
| title_fullStr |
Distilled-MobileNet Model of Convolutional Neural Network Simplified Structure for Plant Disease Recognition |
| title_full_unstemmed |
Distilled-MobileNet Model of Convolutional Neural Network Simplified Structure for Plant Disease Recognition |
| title_sort |
distilled-mobilenet model of convolutional neural network simplified structure for plant disease recognition |
| publisher |
Editorial Office of Smart Agriculture |
| publishDate |
2021 |
| url |
https://doaj.org/article/f84d60be63634dc9b10de6e32d98663f |
| work_keys_str_mv |
AT qiuwenjie distilledmobilenetmodelofconvolutionalneuralnetworksimplifiedstructureforplantdiseaserecognition AT yejin distilledmobilenetmodelofconvolutionalneuralnetworksimplifiedstructureforplantdiseaserecognition AT huliangqing distilledmobilenetmodelofconvolutionalneuralnetworksimplifiedstructureforplantdiseaserecognition AT yangjuan distilledmobilenetmodelofconvolutionalneuralnetworksimplifiedstructureforplantdiseaserecognition AT liqili distilledmobilenetmodelofconvolutionalneuralnetworksimplifiedstructureforplantdiseaserecognition AT mojianyou distilledmobilenetmodelofconvolutionalneuralnetworksimplifiedstructureforplantdiseaserecognition AT yiwanmao distilledmobilenetmodelofconvolutionalneuralnetworksimplifiedstructureforplantdiseaserecognition |
| _version_ |
1718425903216721920 |