基于低时延和高精度脉冲神经网络的目标检测
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:


Target Detection Based on Low Latency and High Accuracy Spiking Neural Network
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 增强出版
  • |
  • 文章评论
    摘要:

    人工神经网络(artificial neural network, ANN)在众多领域取得了显著进展, 但其对计算资源和能耗的高需求限制了其在硬件端的部署和应用. 脉冲神经网络(spiking neural network, SNN)因其低功耗和快速推理的特性, 在神经形态硬件上表现出色. 然而, SNN的神经元动态和脉冲发放机制导致其训练过程复杂, 目前主要研究集中在图像分类任务上, 本文尝试将SNN应用于更为复杂的计算机视觉任务. 本文以YOLOv3-tiny网络为基础, 提出了Spiking YOLOv3模型, 其符合SNN特性的网络模型, 在检测任务上实现了更高的准确度, 并将平均推理时间减少至约原来工作的1/4. 此外, 我们还分析了ANN-SNN转换过程中产生的转换误差, 并采用量化激活函数对Spiking YOLOv3模型进行了优化以减小转换误差. 优化后的模型平均推理时间减少至约原来的1/2, 并在VOC与UAV数据集上实现在ANN-SNN无损转换, 显著提升了基于该模型的检测效率.

    Abstract:

    Artificial neural network (ANN) has made significant progress in many fields, but its high demand for computing resources and energy consumption limits its deployment and application on the hardware side. Spiking neural network (SNN) performs well on neural morphology hardware due to its low power consumption and fast inference characteristics. However, the neural dynamics and pulse propagation mechanism of SNN make its training process complex. Current research primarily focuses on image classification tasks. This study attempts to apply SNN to more complex computer vision tasks. This study is based on the YOLOv3 tiny network and proposes the spiking YOLOv3 model, which conforms to the SNN characteristics of the network model. It achieves higher accuracy in detection tasks and reduces the average inference time to about 1/4 of the original work. In addition, this study also analyzes the conversion errors generated during the ANN-SNN conversion process and optimizes the Spiking YOLOv3 model using a quantization activation function to reduce conversion errors. The optimized model reduces the average inference time to about half of the original and achieves lossless conversion on the VOC and UAV datasets in ANN-SNN, significantly improving the detection efficiency based on this model.

    参考文献
    相似文献
    引证文献
引用本文

明晓钰,李翔宇.基于低时延和高精度脉冲神经网络的目标检测.计算机系统应用,,():1-10

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-01-11
  • 最后修改日期:2024-02-07
  • 录用日期:
  • 在线发布日期: 2024-05-31
  • 出版日期:
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号