| 注册
首页|期刊导航|电子科技大学学报|联合多连接特征编解码与小波池化的轻量级语义分割

联合多连接特征编解码与小波池化的轻量级语义分割

易清明 王渝 石敏 骆爱文

电子科技大学学报2024,Vol.53Issue(3):366-375,10.
电子科技大学学报2024,Vol.53Issue(3):366-375,10.DOI:10.12178/1001-0548.2023124

联合多连接特征编解码与小波池化的轻量级语义分割

Lightweight Semantic Segmentation by Combining Multi-Link Feature Codec with Wavelet Pooling

易清明 1王渝 2石敏 2骆爱文2

作者信息

  • 1. 暨南大学信息科学技术学院,广州 510632||泰斗微电子科技有限公司,广州 510663
  • 2. 暨南大学信息科学技术学院,广州 510632
  • 折叠

摘要

Abstract

Semantic segmentation is currently one of the basic technologies in the field of scene understanding.Existing semantic segmentation networks usually result in complex structures,a large number of parameters,excessive loss of image feature information,and low computational efficiency.To address these problems,this work proposes a lightweight semantic segmentation network named MLWP-Net(Multi-Link Wavelet-Pooled Network)which combines features with multiple connections and wavelet pooling based on the encoder-decoder framework and Discrete Wavelet Transform(DWT).In the encoding phase,a lightweight feature extraction bottleneck is designed by combining with the depthwise separable convolution,dilated convolution,and channel compression,using a multi-link strategy to fuse multi-level features;besides,a low-frequency-mixed wavelet pooling operation is employed to replace the traditional downsampling operation for effectively reducing the information loss during the encoding process.In the decoding stage,a multi-branch parallel dilated convolutional decoder is designed to fuse multiple features linked to the different layers in the encoder to recover the image resolution in parallel.The experimental results show that our MLWP-Net achieves 74.1%and 68.2%mIoU segmentation accuracy on the datasets of Cityscapes and Camvid with only 0.74M parameters,which demonstrates its effectiveness for semantic segmentation.

关键词

实时语义分割/轻量级神经网络/多连接特征融合/小波池化/多分支空洞卷积

Key words

real-time semantic segmentation/lightweight neural network/multi-link feature fusion/wavelet pooling/multi-branch dilated convolution

分类

信息技术与安全科学

引用本文复制引用

易清明,王渝,石敏,骆爱文..联合多连接特征编解码与小波池化的轻量级语义分割[J].电子科技大学学报,2024,53(3):366-375,10.

基金项目

国家自然科学基金(62002134) (62002134)

广东省基础与应用基础研究基金(2020A1515110645,2023A1515010834) (2020A1515110645,2023A1515010834)

广东省普通高校新型半导体与器件重点实验室项目(2021KSY001) (2021KSY001)

羊城创新创业领军人才支持计划(2019019) (2019019)

广东省科技创新战略专项(大学生科技创新培育)(pdjh2023b0061) (大学生科技创新培育)

电子科技大学学报

OA北大核心CSTPCD

1001-0548

访问量0
|
下载量0
段落导航相关论文