Home > Papers

Face Recognition based on Simplified CNN and Median Pooling
XIONG Feng-ye 1, DONG Yuan 1, BAI Hong-liang 2
1. School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876
2. Beijing FaceALL Technology Ltd., Beijing 100082
*Correspondence author
#Submitted by
Funding: none
Opened online:20 October 2016
Accepted by: none
Citation: XIONG Feng-ye, DONG Yuan, BAI Hong-liang.Face Recognition based on Simplified CNN and Median Pooling[OL]. [20 October 2016] http://en.paper.edu.cn/en_releasepaper/content/4706549
Convolution neural network(CNN) is increasingly used by the groups studying face recognition. CNN dramatically improves the performance on many datasets such as LFW and IJB-A. But most of the groups extract features from big networks with large amount of parameters and FLOPS. In this work, a simplified CNN architecture, which achieves comparable results to the state of the art, with only 0.8M training data, 4.4M parameters and 0.6B FLOPS, is proposed. In addition, an anti-noise median pooling method is introduced when dealing with template-based comparison.
Keywords:Computer Application Technology, Deep Learning, Convolutional Neural Network, Face Recognition

For this paper

  • PDF (4KB)
  • ● Revision 0   
  • ● Print this paper
  • ● Recommend this paper to a friend
  • ● Add to my favorite list

    Saved Papers

    Please enter a name for this paper to be shown in your personalized Saved Papers list


Add yours

Related Papers


PDF Downloaded 123
Bookmarked 0
Recommend 0
Comments Array
Submit your papers