Design of Convolutional Network Based on Slice

ZHOU Yue; ZENG Shang-you; YANG Yuan-fei; FENG Yan-yan; PAN Bing

Chinese

您当前的位置：

首页 >

文章列表页 >

Design of Convolutional Network Based on Slice

更新时间：2026-09-04

- Design of Convolutional Network Based on Slice
- Vol. 36, Issue 2, Pages: 68-72(2019)
- 作者机构：
  
  广西师范大学机构电子工程学院,广西,桂林,541004
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2019
- 稿件说明：
移动端阅览
周悦, 曾上游, 杨远飞, 冯燕燕, 潘兵. 基于分组模块的卷积神经网络设计[J]. 微电子学与计算机, 2019, 36(2): 68-72.

ZHOU Yue, ZENG Shang-you, YANG Yuan-fei, et al. Design of Convolutional Network Based on Slice[J]. 2019, 36(2): 68-72.
周悦, 曾上游, 杨远飞, 冯燕燕, 潘兵. 基于分组模块的卷积神经网络设计[J]. 微电子学与计算机, 2019, 36(2): 68-72. DOI：

ZHOU Yue, ZENG Shang-you, YANG Yuan-fei, et al. Design of Convolutional Network Based on Slice[J]. 2019, 36(2): 68-72. DOI：

摘要

本文提出了一种基于分组模块的卷积结构

先将输出特征图分成数量相等的两组

每一组采用不同的卷积核进行操作以提取更充分的信息

而后将分组得到的多样性特征图像进行级联

最后通过1*1的卷积核将所有特征图整合.与传统的CNN比较

使用本文模块的网络在数据集Caltech256上将识别率由50.1%提升至52.2%.在数据集101_food上将识别精度由66.3%提升至68.9%.实验结果表明网络在识别精度性能上有所提升.

Abstract

This paper proposes a grouping method of convolution structure for feature extraction of images. The model increases the depth of network

and the network parameters changes smaller. Compared with the traditional CNN

the network using the module of this paper increases the recognition rate from 50.1% to 52.2% on the data set Caltech256. On the data set 101_food

the recognition accuracy increased from 66.3% to 68.9%. Experimental results show that the network structure in the paper improves the network performance.

关键词

Keywords

references

Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]// International Conference on International Conference on Machine Learning. JMLR.org, 2015.

Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems. 2012: 1097-1105.

Hinton G E, Salakhutdinov R R. Reducing the Dimensionality of Data with Neural Networks[J]. Science, 2006, 313(5786):504. DOI: 504

Jia Y, Shelhamer E, Donahue J, et al. Caffe: Convolutional Architecture for Fast Feature Embedding[C]// ACM International Conference on Multimedia. ACM, 2014: 675-678.

Lecuny, Bottou L, Bengio Y, et al.Geadient-based learning applied to document recognition[J].Pr Oceeding of the IEEE, 1998, 86(11);2278-2324. DOI: 2278

Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]// International Conference on Neural Information Processing Systems. Curran Associates Inc. 2012: 1097-1105.

张顺, 龚怡宏.深度卷积神经网络的发展及其在计算机视觉领域的应用[J].计算机学报, 2017(9).

杨天祺, 黄双喜.改进卷积神经网络在分类与推荐中的实例应用[J].计算机应用研究, 2018, 35(4):974-977. DOI: 974

周飞燕, 金林鹏.卷积神经网络研究综述[J].计算机学报, 2017, 40(6):1229-1251. DOI: 1229

杨远飞, 曾上游.基于并行和切片的深度卷积网络设计研究[J].微电子学与计算机, 2018, 35(3):120-124. DOI: 120

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A spherical perception-based panoramic image saliency prediction algorithm with longitude weighting

CNN inference task division and memory scheduling algorithm based on tiling subgraph

Design of PCNN_LSTM hardware accelerator for SOC estimation of lithium batteries

Research on SAR image denoising technology based on U-Net network structure

Dynamic gesture recognition based on lightweight (2+1)D convolution structure

Related Author

CHEN Ziyi

LU Chenglong

LAN Hong

CHEN Song

GE Mengke

WANG Junpeng

CHENG Ran

WU Hao

Related Institution

School of Information Engineering, Jiangxi University of Science and Technology

School of Microelectronics, University of Science and Technology of China

Institute of Artificial Intelligence, Hefei Comprehensive National Science Center

School of Computer Science and Technology, Anhui University

College of Electronics Engineering/International Semiconductor College, Chongqing University of Posts and Telecommunications

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰