测试技术学报2024，Vol.38Issue(4)：448-454,7.DOI:10.3969/j.issn.1671-7449.2024058
BiUNet:基于双层路由注意力的轻量化医学分割网络
BiUNet:Lightweight Medical Segmentation Network Based on Bi-Level Routing Attention
王莹 1吴本阳 2郭晋川 2张萌 2原锌蕾3
作者信息
- 1. 山西大学 电力与建筑学院,山西 太原 030006
- 2. 山西大学 物理电子工程学院,山西 太原 030006
- 3. 山西财经大学 管理科学与工程学院,山西 太原 030006
- 折叠
摘要
Abstract
To solve the problems of high computing cost and slow model training in vision Transformer backbone extraction network,and to further improve the performance of Transformer structure in the field of medical image segmentation,a new lightweight U-architecture medical image segmentation network named BiUNet was proposed.The input medical image was cut into several blocks,and then the blocks were fed into the BiFormer based on the dynamic sparse attention mechanism of Bi-level routing.By com-bining downsampling and BiFormer modules with a specific number of blocks,a multi-level pyramid struc-ture was constructed to achieve feature extraction.Subsequently,the feature map output from the encoder was decoded by a multi-level pyramid structure which was constructed by combining the upsampling and convolution modules,and pixel-level semantic segmentation was realized.The model achieved 90.2%,93.7%and 85.6%mIoU values as well as 5.55 G Flops and 28.10 M parameters on the three medical datasets sequentially.The results show that BiUNet can effectively improve the accuracy of medical image segmentation with a lightweight effect.关键词
双层路由注意力机制/Transformer结构/医学图像分割/轻量级/U型结构Key words
Bi-level routed attention mechanism/transformer structure/medical image segmentation/lightweight/U-shaped structure分类
信息技术与安全科学引用本文复制引用
王莹,吴本阳,郭晋川,张萌,原锌蕾..BiUNet:基于双层路由注意力的轻量化医学分割网络[J].测试技术学报,2024,38(4):448-454,7.
