Discovering class-wise trends of max-pooling in subspace

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

The traditional max-pooling operation in Convolutional Neural Networks (CNNs) only obtains the maximal value from a pooling window. However, it discards the information about the precise position of the maximal value. In this paper, we extract the location of the maximal value in a pooling window and transform it into 'displacement feature'. We analyze and discover the class-wise trend of the displacement features in many ways. The experimental results and discussion demonstrate that the displacement features have beneficial behaviors for solving the problems in max-pooling.

Original languageEnglish
Title of host publicationProceedings - 2018 16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages98-103
Number of pages6
ISBN (Electronic)9781538658758
DOIs
Publication statusPublished - Dec 5 2018
Event16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018 - Niagara Falls, United States
Duration: Aug 5 2018Aug 8 2018

Publication series

NameProceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR
Volume2018-August
ISSN (Print)2167-6445
ISSN (Electronic)2167-6453

Other

Other16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018
Country/TerritoryUnited States
CityNiagara Falls
Period8/5/188/8/18

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Discovering class-wise trends of max-pooling in subspace'. Together they form a unique fingerprint.

Cite this