###
计算机系统应用:2020,29(9):178-183
本文二维码信息
码上扫一扫!
基于改进Deeplab V3+网络的语义分割
(长安大学 信息工程学院, 西安 710064)
Semantic Segmentation Based on Improved Deeplab V3+ Network
(School of Information Engineering, Chang’an University, Xi’an 710064, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 122次   下载 75
投稿时间:2019-12-12    修订日期:2020-02-08
中文摘要: 深度学习的语义分割在计算机视觉领域中有非常广阔的发展前景,但许多分割效果较好网络模型占用内存大和处理单张图片耗时长.针对这个问题,把Deeplab V3+模型的骨干网(ResNet101)的瓶颈单元设计为1D非瓶颈单元,且对空洞空间金字塔池化模块(Atrous Spatial Pyramid Pooling,ASPP)的卷积层进行分解.该算法能大幅度降低Deeplab V3+网络的参数量,提高网络推理速度.基于PASCAL VOC 2012数据集进行对比实验,实验结果显示改进网络模型拥有更快的处理速度和更优的分割效果,且消耗更少的内存.
Abstract:Semantic segmentation of deep learning has a very broad development prospect in the field of computer vision, but many network models with better segmentation effects take up a lot of memory and take a long time to process a single picture. In response to this problem, we replace the bottleneck unit of the Deeplab V3+ model backbone network (ResNet101) with a 1D non-bottleneck unit, and decompose the convolutional layer of the Atrous Spatial Pyramid Pooling (ASPP) module. The algorithm can greatly reduce the parameter amount of Deeplab V3+ network and accelerate the speed of network inference. Based on the PASCAL VOC 2012 dataset, the experimental results show that the improved network model has faster speed and better segmentation, and takes up less memory space.
文章编号:7541     中图分类号:    文献标志码:
基金项目:
引用文本:
席一帆,孙乐乐,何立明,吕悦.基于改进Deeplab V3+网络的语义分割.计算机系统应用,2020,29(9):178-183
XI Yi-Fan,SUN Le-Le,HE Li-Ming,LYU Yue.Semantic Segmentation Based on Improved Deeplab V3+ Network.COMPUTER SYSTEMS APPLICATIONS,2020,29(9):178-183

用微信扫一扫

用微信扫一扫