Fig. 4
From: Chinese herbal medicine recognition network based on knowledge distillation and cross-attention
Chinese herbal medicine recognition model based on knowledge distillation and cross-attention. The ShuffleCANet model proposed in this article uses ShuffleNet as the backbone network. In order to reduce the number of model parameters while maintaining detection accuracy, a cross-attention module (blue rectangular area) is proposed. The entire model includes Conv1, Stage2, Stage3, Stage4, Cross-Attention and GlobalPool.
