Chebyshev Pooling: An Alternative Layer for the Pooling of CNNs-Based Classifier

Ka Hou Chan, Giovanni Pau, Sio Kei Im

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Citations (Scopus)

Abstract

The CNNs-based model has been proven to achieve impressive performance on a wide range of classification tasks. However, the convoluted results will only retain the local features and discard the global information when using max-pooling is performed with decreasing resolutions. some features of similar data are always diluted during several convolutions, so the decision will be more difficult after max pooling. In this work, we propose a novel pooling layer called Chebyshev Pooling. It makes use of Chebyshev's inequality to produce results about the probability distributions within the kernel which contains the functions of maximum and average pooling. In addition, the proposed layer can ensure that its output is in the range of (0. 0, 1. 0), which is more stable for subsequent processing. Experiments illustrate that our proposed pooling layer can improve the classification performance of various data sets. Moreover, the design and implementation can be easily deployed in some type of CNNs-based classification systems.

Original languageEnglish
Title of host publication2021 IEEE 4th International Conference on Computer and Communication Engineering Technology, CCET 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages106-110
Number of pages5
ISBN (Electronic)9781665438902
DOIs
Publication statusPublished - 13 Aug 2021
Event4th IEEE International Conference on Computer and Communication Engineering Technology, CCET 2021 - Virtual, Beijing, China
Duration: 13 Aug 202115 Aug 2021

Publication series

Name2021 IEEE 4th International Conference on Computer and Communication Engineering Technology, CCET 2021

Conference

Conference4th IEEE International Conference on Computer and Communication Engineering Technology, CCET 2021
Country/TerritoryChina
CityVirtual, Beijing
Period13/08/2115/08/21

Keywords

  • CNNs-based
  • Chebyshev's inequality
  • Classification
  • Pooling Layer
  • Softplus

Fingerprint

Dive into the research topics of 'Chebyshev Pooling: An Alternative Layer for the Pooling of CNNs-Based Classifier'. Together they form a unique fingerprint.

Cite this