Fully Convolutional Fractional Scaling

Michael Soloveitchik*, Michael Werman

*Corresponding author for this work

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

Abstract

Fully convolutional networks can be applied to any size input but till now do not support non-integer scaling. We introduce a fully convolutional fractional scaling component, FCFS. Our architecture is simple with an efficient single layer implementation. Examples and code implementations of three common scaling methods are published.

Original languageAmerican English
Title of host publicationProceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022
EditorsKokou Yetongnon, Albert Dipanda, Luigi Gallo
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages238-245
Number of pages8
ISBN (Electronic)9781665464956
DOIs
StatePublished - 2022
Event16th IEEE International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022 - Dijon, France
Duration: 19 Oct 202221 Oct 2022

Publication series

NameProceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022

Conference

Conference16th IEEE International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022
Country/TerritoryFrance
CityDijon
Period19/10/2221/10/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

  • FCN
  • fractional scaling
  • fully convolutional layer
  • fully convolutional network
  • fully convolutional scaling
  • pixelshuffle
  • scaling

Cite this