• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Cui, Yingxuan (Cui, Yingxuan.) | Shi, Yunhui (Shi, Yunhui.) (学者:施云惠) | Sun, Xiaoyan (Sun, Xiaoyan.) | Yin, Wenbin (Yin, Wenbin.)

收录:

CPCI-S

摘要:

Two dimensional Convolutional Neural Networks (ConvNets) have been widely adopted as powerful models and have achieved state-of-the-art performance in many image related tasks. However, their extensions are still struggling for leading performance for high dimensional (HD) signal processing, partially due to the explosion of training parameters, greatly enhanced computational complexity and memory cost. In this paper, we present a simple, lightweight, yet efficient ConvNet, called S-Net, for the HD signal processing by allowing a separable structure on the ConvNet throughout the learning process. It takes advantage of a series of one dimensional convolution kernels to handle N-dimensional (ND) signals. Thus, the presented S-Net significantly reduces the training complexity, parameters, and memory cost. The proposed S-Net is evaluated on both 2D and 3D benchmarks CIFAR-10 and KTH. Experimental results show that the S-Net achieves competitive performance with greatly reduced computational and memory costs in comparison with the state-of-the-art ConvNet models.

关键词:

memory cost matricization convolution neural network computational complexity S-Net

作者机构:

  • [ 1 ] [Cui, Yingxuan]Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Multimedia & Intelligent Software, Beijing Adv Innovat Ctr Future Internet Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Shi, Yunhui]Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Multimedia & Intelligent Software, Beijing Adv Innovat Ctr Future Internet Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Sun, Xiaoyan]Microsoft Res Asia, Beijing, Peoples R China
  • [ 4 ] [Yin, Wenbin]Harbin Inst Technol, Sch Comp Sci & Technol, Harbin, Heilongjiang, Peoples R China

通讯作者信息:

  • [Cui, Yingxuan]Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Multimedia & Intelligent Software, Beijing Adv Innovat Ctr Future Internet Technol, Beijing 100124, Peoples R China

查看成果更多字段

相关关键词:

相关文章:

来源 :

2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW 2018)

ISSN: 2330-7927

年份: 2018

语种: 英文

被引次数:

WoS核心集被引频次: 0

SCOPUS被引频次:

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 0

在线人数/总访问数:484/4912328
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司