Energy-Efficient Spiking Segmenter for Frame and Event-Based Images

Author:

Zhang Hong1ORCID,Fan Xiongfei1,Zhang Yu12ORCID

Affiliation:

1. State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China

2. Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province, Hangzhou 310027, China

Abstract

Semantic segmentation predicts dense pixel-wise semantic labels, which is crucial for autonomous environment perception systems. For applications on mobile devices, current research focuses on energy-efficient segmenters for both frame and event-based cameras. However, there is currently no artificial neural network (ANN) that can perform efficient segmentation on both types of images. This paper introduces spiking neural network (SNN, a bionic model that is energy-efficient when implemented on neuromorphic hardware) and develops a Spiking Context Guided Network (Spiking CGNet) with substantially lower energy consumption and comparable performance for both frame and event-based images. First, this paper proposes a spiking context guided block that can extract local features and context information with spike computations. On this basis, the directly-trained SCGNet-S and SCGNet-L are established for both frame and event-based images. Our method is verified on the frame-based dataset Cityscapes and the event-based dataset DDD17. On the Cityscapes dataset, SCGNet-S achieves comparable results to ANN CGNet with 4.85 × energy efficiency. On the DDD17 dataset, Spiking CGNet outperforms other spiking segmenters by a large margin.

Funder

STI 2030-Major Projects

Autonomous Intelligent Unmanned Systems

Publisher

MDPI AG

Subject

Molecular Medicine,Biomedical Engineering,Biochemistry,Biomaterials,Bioengineering,Biotechnology

Reference68 articles.

1. Cgnet: A light-weight context guided network for semantic segmentation;Wu;IEEE Trans. Image Process.,2020

2. SegFormer: Simple and efficient design for semantic segmentation with transformers;Xie;Adv. Neural Inf. Process. Syst.,2021

3. Isomorphic model-based initialization for convolutional neural networks;Zhang;J. Vis. Commun. Image Represent.,2022

4. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.

5. Binas, J., Neil, D., Liu, S.C., and Delbruck, T. (2017). DDD17: End-to-end DAVIS driving dataset. arXiv.

Cited by 2 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

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