Semantic segmentation algorithm based on separable dilated convolution and joint normalization method

XIONG Wei; TONG Lei; LI Li-rong; LI Ming

Chinese

您当前的位置：

首页 >

文章列表页 >

Semantic segmentation algorithm based on separable dilated convolution and joint normalization method

更新时间：2026-09-04

- Semantic segmentation algorithm based on separable dilated convolution and joint normalization method
- Vol. 37, Issue 10, Pages: 18-23(2020)
- 作者机构：
  
  1. 湖北工业大学机构电气与电子工程学院,湖北,武汉,430068
  2. 美国南卡罗来纳大学计算机科学与工程系，南卡,哥伦比亚,29201
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2020
- 稿件说明：
移动端阅览
熊炜, 童磊, 李利荣, 李敏. 基于可分离空洞卷积与联合归一化的语义分割算法研究[J]. 微电子学与计算机, 2020, 37(10): 18-23.

XIONG Wei, TONG Lei, LI Li-rong, et al. Semantic segmentation algorithm based on separable dilated convolution and joint normalization method[J]. 2020, 37(10): 18-23.
熊炜, 童磊, 李利荣, 李敏. 基于可分离空洞卷积与联合归一化的语义分割算法研究[J]. 微电子学与计算机, 2020, 37(10): 18-23. DOI：

XIONG Wei, TONG Lei, LI Li-rong, et al. Semantic segmentation algorithm based on separable dilated convolution and joint normalization method[J]. 2020, 37(10): 18-23. DOI：

摘要

图像语义分割是图像理解的重要一环，已被广泛应用于自动驾驶等场景中.针对信息丢失和语义分割速度慢的问题，本文提出一种基于可分离空洞卷积和联合归一化的语义分割算法.首先结合可分离卷积和空洞卷积提取ResNet101的后三层输出，然后在语义分割中应用实例归一化方法，与应用批量归一化对比，验证了实例归一化的有效性，最后提出了两种联合归一化方法，验证了这两种归一化方法对语义分割效果的提升.本文方法在Pascal VOC 2012数据集进行了实验，结果表明，本文方法加速了网络的训练、验证和预测，交并集之比最高到达了80.62%.

Abstract

Image semantic segmentation is an important part of image understanding

which is applied to automatic driving. In this paper

we use the Pascal VOC 2012 data set and ResNet101 as the basic network.We propose semantic segmentation algorithm based on separable dilated convolution and improved normalization method to solve the problem of information loss andslow speed Firstly

we combineseparable convolution and dilated convolution to extract the last three layers output of ResNet101.Compared with standard dilatedconvolution

separable dilatedconvolution accelerates the training

validation and prediction of the network. Then

in the semantic segmentation

the instance normalization method is applied and compared with the application batch normalization to verify the effectiveness of batch normalization. Finally

two normalization methods combining batch normalizationand instance normalizationare proposed to improve the effect of semantic segmentation. This method is tested in Pascal VOC 2012 data set. The results show thatour methodaccelerates the training

validation and prediction of the network. Thehighest mean intersection over union ofthis method in Pascal VOC 2012 data set is 80.62%.

关键词

Keywords

references

ZHAO H S, SHI J P, QI X J, et al. Pyramid scene parsing network [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 6230-6239.

CHAURASIA A, CULURCIELLO E. LinkNet: Exploiting encoder representations for efficient semantic segmentation [C]// Proceedings of the 2017 IEEE Visual Communications and Image Processing (VCIP), St. Petersburg, FL, USA, 2017: 1-4.

CHEN L C, ZHU Y K, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation [C]// Proceedings of the 2018 European Conference on Computer Vision (ECCV), Munich Germany, 2018: 801-818.

LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation [C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Boston, MA, USA, 2015: 3431-3440.

CHEN Z. Research on semantic segmentation based on convolutional neural network [D]. Beijin: Beijing Jiaotong University, 2018.

HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Las Vegas, NV, USA, 2016: 770-778.

YU C Q, WANG J B, PENG C, et al. Learning a discriminative feature network for semantic segmentation [C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), Salt Lake City, UT, USA, 2018: 1857-1866.

Views

109

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on assembly action recognition based on MSS-YOLO-MPHands fusion architecture

Monte carlo analysis of V-layout trench SiC neutron detector

Design of ultra-low power real-time clock circuits

Steganography model guided by attention mechanism and improved dense convolution

Research on the design of blockchain-based AI-generated content traceability framework

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰