计算机工程与科学2026，Vol.48Issue(5)：898-905,8.DOI:10.3969/j.issn.1007-130X.2026.05.013
基于注意力机制的特征融合语义分割模型
A feature fusion semantic segmentation model based on attention mechanism
摘要
Abstract
To address the issues of mis-segmentation,low segmentation accuracy,and severe loss of detailed information commonly encountered in the existing DeepLabV3+semantic segmentation model,a feature-fusion semantic segmentation model based on an attention mechanism is proposed.Firstly,a switchable atrous convolution is cascaded within the dilated convolution branch of the model,enabling it to adapt more flexibly to features at different scales and thereby reducing mis-segmentation.Additional-ly,an RFEM module is introduced to capture multi-scale information from shallow features and depen-dencies across different ranges,enhancing the model's performance.Furthermore,intermediate-layer features of the model are extracted and fused with its deep features using the ELAFF module,enabling the model to recover detailed information lost during the downsampling process.Finally,an efficient lo-cal attention mechanism is added to make the model focus more on image information and reduce back-ground interference.Experimental results on the PASCAL VOC 2012 dataset demonstrate that,com-pared to the original model,the proposed model achieves a 2.36 percentage points increase in mean intersection-over-union(mIoU)and a 1.60 percentage points improvement in mean pixel accuracy(MPA),effectively enhancing the model's segmentation performance.关键词
注意力机制/语义分割/DeepLabV3+/特征融合Key words
attention mechanism/semantic segmentation/DeepLabV3+/feature fusion分类
信息技术与安全科学引用本文复制引用
马冬梅,朱启荣,吕雪龙..基于注意力机制的特征融合语义分割模型[J].计算机工程与科学,2026,48(5):898-905,8.基金项目
国家自然科学基金(61961037) （61961037）
