气候变化领域集成服务门户(CCPortal): EDKSANet: An Efficient Dual-Kernel Split Attention Neural Network for the Classification of Tibetan Medicinal Materials

CCPortal

DOI	10.3390/electronics12204330
	EDKSANet: An Efficient Dual-Kernel Split Attention Neural Network for the Classification of Tibetan Medicinal Materials
	Qi, Jindong; Wangdui, Bianba; Jiang, Jun; Yang, Jie; Zhou, Yanxia
发表日期	2023
EISSN	2079-9292
卷号	12 期号:20
英文摘要	Tibetan medicine has received wide acclaim for its unique diagnosis and treatment methods. The identification of Tibetan medicinal materials, which are a vital component of Tibetan medicine, is a key research area in this field. However, traditional deep learning-based visual neural networks face significant challenges in efficiently and accurately identifying Tibetan medicinal materials due to their large number, complex morphology, and the scarcity of public visual datasets. To address this issue, we constructed a computer vision dataset with 300 Tibetan medicinal materials and proposed a lightweight and efficient cross-dimensional attention mechanism, the Dual-Kernel Split Attention (DKSA) module, which can adaptively share parameters of the kernel in both spatial and channel dimensions. Based on the DKSA module, we achieve efficient unification of convolution and self-attention under the CNN architecture and develop a new lightweight backbone architecture, EDKSANet, to provide enhanced performance for various computer vision tasks. As compared to RedNet, the top-1 accuracy is improved by 1.2% on an ImageNet dataset, and a larger margin of +1.5 box AP for object detection and an improvement of +1.3 mask AP for instance segmentation on MS-COCO dataset are obtained. Moreover, EDKSANet achieved excellent classification performance on the Tibetan medicinal materials dataset, with an accuracy of up to 96.85%.
关键词	Tibetan medicinal materials efficient cross-dimensional attention efficient unification EDKSANet excellent classification performance
WOS研究方向	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Physics, Applied
WOS记录号	WOS:001089789300001
来源期刊	ELECTRONICS
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/283793
作者单位	Tibet University; Tibet University
推荐引用方式 GB/T 7714	Qi, Jindong,Wangdui, Bianba,Jiang, Jun,et al. EDKSANet: An Efficient Dual-Kernel Split Attention Neural Network for the Classification of Tibetan Medicinal Materials[J],2023,12(20).
APA	Qi, Jindong,Wangdui, Bianba,Jiang, Jun,Yang, Jie,&Zhou, Yanxia.(2023).EDKSANet: An Efficient Dual-Kernel Split Attention Neural Network for the Classification of Tibetan Medicinal Materials.ELECTRONICS,12(20).
MLA	Qi, Jindong,et al."EDKSANet: An Efficient Dual-Kernel Split Attention Neural Network for the Classification of Tibetan Medicinal Materials".ELECTRONICS 12.20(2023).