计算机应用与软件2025，Vol.42Issue(4)：311-318,334,9.DOI:10.3969/j.issn.1000-386x.2025.04.044
GMFNet:全局多尺度和多级别的特征融合语义分割网络
GMFNET:GLOBAL MULTI-SCALE AND MULTI-LEVEL FEATURE FUSION NETWORK FOR SEMANTIC SEGMENTATION
摘要
Abstract
For the semantic segmentation network,the following problems exist in the fusion of low-level and high-level feature in the encoder-decoder:(1)feature extraction in space and channel cannot be synchronized,resulting in feature combinations that cannot obtain global context information;(2)feature fusion cannot be fully utilized low-level and high-level feature images,resulting in blurred semantic boundaries.The global atrous spatial pyramid pooling was designed.This structure not only extracted multi-scale information in space and utilized image information in channels,but also enhanced feature reuse in the encoder stage.A feature fusion attention module was designed to connect low-level and high-level features and new features at different stages in the encoder.Experiments show that the algorithm achieves 77.92％mIoU on the Cityscapes dataset.关键词
语义分割/卷积神经网络/全局上下文信息/特征融合/编码器-解码器Key words
Semantic segmentation/Convolutional neural network/Global context information/Feature fusion/Encoder-decoder分类
计算机与自动化引用本文复制引用
陈金令,赵成明,李洁..GMFNet:全局多尺度和多级别的特征融合语义分割网络[J].计算机应用与软件,2025,42(4):311-318,334,9.基金项目
成都市科技局创新创业资助项目(2018YF0500893GX). （2018YF0500893GX）
