电子科技2025，Vol.38Issue(5)：83-88,6.DOI:10.16180/j.cnki.issn1007-7820.2025.05.012
融合通道全局注意力机制的双路径实时语义分割
Dual-Path Real-Time Semantic Segmentation Network with Channel-Level Global Attention Mechanism
摘要
Abstract
In view of the problems of the mainstream real-time semantic segmentation methods,such as poor multi-scale feature extraction ability,weak feature extraction ability of lightweight backbone network,and lack of effective fusion of context information,a two-path real-time semantic segmentation model with global attention mechanism is proposed in this study.The FPPM(Fast Pyramid Pooling Module)is lightweight based on the PPM(Pyramid Pooling Module)to improve the speed of the module while maintaining multi-scale information extraction.Spatial information branching can compensate for the performance loss caused using lightweight backbone networks.The channel global attention mechanism effectively integrates spatial information and semantic information extracted by backbone network,and interacts with global information to improve the segmentation performance of the model.Without pre-training with other data sets,the proposed model achieves 73.8%average cross ratio on PASCAL VOC2012 validation data set with14.6 MB of reference,and reaches 43 frame∙s-1 on NVIDIA TITAN Xp,which indicates that the model achieves a good balance in accuracy and speed.关键词
语义分割/双路径/注意力机制/多尺度池化/实时/深度学习/信息融合/轻量化Key words
semantic segmentation/dual-path/attention mechanism/multi-scale pooling/real-time/deep learning/information fusion/lightweight分类
信息技术与安全科学引用本文复制引用
胡锦磊,田恩刚,瞿枫..融合通道全局注意力机制的双路径实时语义分割[J].电子科技,2025,38(5):83-88,6.基金项目
国家自然科学基金(62173231) National Natural Science Foundation of China(62173231) （62173231）
