CCF Chinese Conference on Computer Vision

Computer Vision pp 406-416

A Sparse Pyramid Pooling Strategy

  • Lu Wang
  • Shengrong Gong
  • Chunping Liu
  • Yi Ji
  • Mengye Song
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 547)

Abstract

In this paper, we introduce a more principled pooling strategy for the Convolutional Restricted Boltzmann Machine. In order to solve the information loss problem of pooling operation and inspired by the idea of spatial pyramid, we replace the probabilistic max-pooling with our sparse pyramid pooling, which produces outputs of different sizes for different pyramid levels. And then we use sparse coding method to aggregate the multi-level feature maps. The experimental results on KTH action dataset and Maryland dynamic scenes dataset show that the sparse pyramid pooling achieves superior performance to the conventional probabilistic max-pooling. In addition, our pooling strategy can effectively improve the performance of deep neural network on video classification.

Keywords

Probabilistic max-pooling Spatial pyramid pooling Sparse coding Deep neural network 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Lu Wang
    • 1
  • Shengrong Gong
    • 1
  • Chunping Liu
    • 1
  • Yi Ji
    • 1
  • Mengye Song
    • 1
  1. 1.School of Computer Science &TechnologySoochow UniversitySuzhouChina

Personalised recommendations