Journal: Scientific Reports

Article Title: Chinese herbal medicine recognition network based on knowledge distillation and cross-attention

doi: 10.1038/s41598-025-85697-6

Figure Lengend Snippet: Performance comparison of different models.

Article Snippet: In 2020, Huang et al. built a dataset containing five classes of Chinese herbal medicines by crawling Baidu images and, based on this dataset, proposed a Chinese herbal medicine image classification method based on the AlexNet model. Hu et al. drew on the concept of multi-task learning, using neural networks as the foundation and traditional features as a supplement, integrating the two to establish a new deep learning model, and collected 200 classes of Chinese herbal slices for Chinese herbal slice recognition.

Techniques: Comparison