The final, formatted version of the article will be published soon.
ORIGINAL RESEARCH article
Front. Plant Sci.
Sec. Technical Advances in Plant Science
Volume 15 - 2024 |
doi: 10.3389/fpls.2024.1433543
This article is part of the Research Topic Emerging Sustainable and Green Technologies for Improving Agricultural Production View all 11 articles
Compressing recognition network of cotton disease with spot-adaptive knowledge distillation
Provisionally accepted- 1 College of Electrical and Mechanical Engineering, Gansu Agricultural University, Lanzhou, Gansu Province, China
- 2 Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China
- 3 National Nanfan Research Institute, Chinese Academy of Agricultural Sciences, Sanya, China
Deep networks play a crucial role in the recognition of agricultural diseases. However, these networks often come with numerous parameters and large sizes, posing a challenge for direct deployment on resource-limited edge computing devices for plant protection robots. To tackle this challenge for recognizing cotton diseases on the edge device, we adopt knowledge distillation to compress the big networks, aiming to reduce the number of parameters and the computational complexity of the networks. In order to get excellent performance, we conduct combined comparison experiments from three aspects: teacher network, student network and distillation algorithm. The teacher networks contain three classical convolutional neural networks, while the student networks include six lightweight networks in two categories of homogeneous and heterogeneous structures. In addition, we investigate nine distillation algorithms using spot-adaptive strategy. The results demonstrate that the combination of DenseNet40 as the teacher and ShuffleNetV2 as the student show best performance when using NST algorithm, yielding a recognition accuracy of 90.59% and reducing FLOPs from 0.29 G to 0.045 G. The proposed method can facilitate the lightweighting of the model for recognizing cotton diseases while maintaining high recognition accuracy and offer a practical solution for deploying deep models on edge computing devices.
Keywords: cotton diseases, deep learning, Model compression, Knowledge distillation, spot-adaptive
Received: 16 May 2024; Accepted: 05 Sep 2024.
Copyright: © 2024 Zhang, Quan, Zhu, Liang and Zhang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Feng Quan, College of Electrical and Mechanical Engineering, Gansu Agricultural University, Lanzhou, 730070, Gansu Province, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.