posted on 2024-04-17, 08:49authored byLu Zheng, Wenhan Long, Junchao Yi, Lu Liu, Ke Xu
The identification and classification of traditional Chinese herbal medicines demand significant time and expertise. We propose the dual-teacher supervised decay (DTSD) approach, an enhancement for Chinese herbal medicine recognition utilizing a refined knowledge distillation model. The DTSD method refines output soft labels, adapts attenuation parameters, and employs a dynamic combination loss in the teacher model. Implemented on the lightweight MobileNet_v3 network, the methodology is deployed successfully in a mobile application. Experimental results reveal that incorporating the exponential warmup learning rate reduction strategy during training optimizes the knowledge distillation model, achieving an average classification accuracy of 98.60% for 10 types of Chinese herbal medicine images. The model boasts an average detection time of 0.0172 s per image, with a compressed size of 10 MB. Comparative experiments demonstrate the superior performance of our refined model over DenseNet121, ResNet50_vd, Xception65, and EfficientNetB1. This refined model not only introduces an approach to Chinese herbal medicine image recognition but also provides a practical solution for lightweight models in mobile applications.
Funding
Special Project on Regional Collaborative Innovation in Xinjiang Uygur Autonomous Region (Science and Technology Aid Program) 2022E02035
Hubei Provincial Administration of Traditional Chinese Medicine Research Project on Traditional Chinese Medicine (ZY2023M064)
Wuhan knowledge innovation special Dawn project (2023010201020465)
National innovation and entrepreneurship training program for college students (202310524017)