Mask-Based Selective Downsampling in Convolutional Neural Networks 


Vol. 50,  No. 5, pp. 722-724, May  2025
10.7840/kics.2025.50.5.722


PDF Full-Text
  Abstract

This letter presents a study on selective down-sampling techniques designed to enhance the efficiency of convolutional neural networks (CNNs). By selectively adjusting the resolution of feature layers based on the down-sampling mask, this method aims to improve efficiency. We develop a network that is 80% lighter than the baseline scheme, and introduce several methods to mitigate the performance degradation of light weight networks. The performance of the proposed methods is evaluated through extensive experiments.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

C. Kwak and S. Bahk, "Mask-Based Selective Downsampling in Convolutional Neural Networks," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 5, pp. 722-724, 2025. DOI: 10.7840/kics.2025.50.5.722.

[ACM Style]

Chulyoung Kwak and Saewoong Bahk. 2025. Mask-Based Selective Downsampling in Convolutional Neural Networks. The Journal of Korean Institute of Communications and Information Sciences, 50, 5, (2025), 722-724. DOI: 10.7840/kics.2025.50.5.722.

[KICS Style]

Chulyoung Kwak and Saewoong Bahk, "Mask-Based Selective Downsampling in Convolutional Neural Networks," The Journal of Korean Institute of Communications and Information Sciences, vol. 50, no. 5, pp. 722-724, 5. 2025. (https://doi.org/10.7840/kics.2025.50.5.722)
Vol. 50, No. 5 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880