Compressing recognition network of cotton disease with spot-adaptive knowledge distillation.

Abstract

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.

Plant phenotyping relevance

綿花の病害状態を画像認識するモデルの軽量化・比較評価が中心であり、植物病害フェノタイピング手法の開発・検証に該当する。

Code and data availability

The paper's key paper-specific asset is the self-built cotton disease dataset (SCDD, 2,151 images, 8 classes) used for all phenotyping/recognition experiments. It is not publicly deposited; the data availability statement only says the raw data will be made available by the authors upon request. No author analysis code

No evidence-backed public reproduction asset is currently recorded.