Hybrid Spiking Fully Convolutional Neural Network for Semantic Segmentation

Author:

Zhang Tao1,Xiang Shuiying12ORCID,Liu Wenzhuo1,Han Yanan1,Guo Xingxing1,Hao Yue2

Affiliation:

1. State Key Laboratory of Integrated Service Networks, Xidian University, Xi’an 710071, China

2. State Key Discipline Laboratory of Wide Bandgap Semiconductor Technology, Xidian University, Xi’an 710071, China

Abstract

The spiking neural network (SNN) exhibits distinct advantages in terms of low power consumption due to its event-driven nature. However, it is limited to simple computer vision tasks because the direct training of SNNs is challenging. In this study, we propose a hybrid architecture called the spiking fully convolutional neural network (SFCNN) to expand the application of SNNs in the field of semantic segmentation. To train the SNN, we employ the surrogate gradient method along with backpropagation. The accuracy of mean intersection over union (mIoU) for the VOC2012 dataset is higher than that of existing spiking FCNs by almost 30%. The accuracy of mIoU can reach 39.6%. Moreover, the proposed hybrid SFCNN achieved excellent segmentation performance for other datasets such as COCO2017, DRIVE, and Cityscapes. Our hybrid SFCNN is a valuable and interesting contribution to extending the functionality of SNNs, especially for power-constrained applications.

Funder

National Key Research and Development Program of China

National Natural Science Foundation of China

National Outstanding Youth Science Fund Project of National Natural Science Foundation of China

The Fundamental Research Funds for the Central Universities

Publisher

MDPI AG

Subject

Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. OdCFU-Net for Brain Tumor Segmentation Based on MRI;2024 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA);2024-06-14

2. Spiking SiamFC++: deep spiking neural network for object tracking;Nonlinear Dynamics;2024-04-03

3. BIR-Net: A Lightweight and Efficient Bilateral Interaction Road Extraction Network;IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3