Improved lightweight identification of agricultural diseases based on MobileNetV3
It addresses the challenge of deploying pest identification models to embedded devices for agricultural applications, but it is incremental as it builds on an existing method.
This paper tackles the problem of lightweight identification of agricultural diseases by introducing a Coordinate Attention block into MobileNetV3, resulting in reduced parameters and model size (e.g., up to 23.4% reduction) with slight accuracy improvements (e.g., up to 0.92% increase).
At present, the identification of agricultural pests and diseases has the problem that the model is not lightweight enough and difficult to apply. Based on MobileNetV3, this paper introduces the Coordinate Attention block. The parameters of MobileNetV3-large are reduced by 22%, the model size is reduced by 19.7%, and the accuracy is improved by 0.92%. The parameters of MobileNetV3-small are reduced by 23.4%, the model size is reduced by 18.3%, and the accuracy is increased by 0.40%. In addition, the improved MobileNetV3-small was migrated to Jetson Nano for testing. The accuracy increased by 2.48% to 98.31%, and the inference speed increased by 7.5%. It provides a reference for deploying the agricultural pest identification model to embedded devices.