Fully Convolutional Fractional Scaling

Michael Soloveitchik; Michael Werman

doi:10.1109/SITIS57111.2022.00050

Fully Convolutional Fractional Scaling

Michael Soloveitchik^*, Michael Werman

^*Corresponding author for this work

The Rachel and Selim Benin School of Engineering and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-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 language	English
Title of host publication	Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022
Editors	Kokou Yetongnon, Albert Dipanda, Luigi Gallo
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	238-245
Number of pages	8
ISBN (Electronic)	9781665464956
DOIs	https://doi.org/10.1109/SITIS57111.2022.00050
State	Published - 2022
Event	16th IEEE International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022 - Dijon, France Duration: 19 Oct 2022 → 21 Oct 2022

Publication series

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

Conference

Conference	16th IEEE International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022
Country/Territory	France
City	Dijon
Period	19/10/22 → 21/10/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

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

Access to Document

10.1109/SITIS57111.2022.00050

Cite this

Soloveitchik, M., & Werman, M. (2022). Fully Convolutional Fractional Scaling. In K. Yetongnon, A. Dipanda, & L. Gallo (Eds.), Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022 (pp. 238-245). (Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SITIS57111.2022.00050

Soloveitchik, Michael ; Werman, Michael. / Fully Convolutional Fractional Scaling. Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022. editor / Kokou Yetongnon ; Albert Dipanda ; Luigi Gallo. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 238-245 (Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022).

@inproceedings{f4a8f6e136d941e1873613a960b19eba,

title = "Fully Convolutional Fractional Scaling",

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.",

keywords = "FCN, fractional scaling, fully convolutional layer, fully convolutional network, fully convolutional scaling, pixelshuffle, scaling",

author = "Michael Soloveitchik and Michael Werman",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 16th IEEE International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022 ; Conference date: 19-10-2022 Through 21-10-2022",

year = "2022",

doi = "10.1109/SITIS57111.2022.00050",

language = "אנגלית",

series = "Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "238--245",

editor = "Kokou Yetongnon and Albert Dipanda and Luigi Gallo",

booktitle = "Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022",

address = "ארצות הברית",

}

Soloveitchik, M & Werman, M 2022, Fully Convolutional Fractional Scaling. in K Yetongnon, A Dipanda & L Gallo (eds), Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022. Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022, Institute of Electrical and Electronics Engineers Inc., pp. 238-245, 16th IEEE International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022, Dijon, France, 19/10/22. https://doi.org/10.1109/SITIS57111.2022.00050

Fully Convolutional Fractional Scaling. / Soloveitchik, Michael; Werman, Michael.
Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022. ed. / Kokou Yetongnon; Albert Dipanda; Luigi Gallo. Institute of Electrical and Electronics Engineers Inc., 2022. p. 238-245 (Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Fully Convolutional Fractional Scaling

AU - Soloveitchik, Michael

AU - Werman, Michael

PY - 2022

Y1 - 2022

N2 - 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.

AB - 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.

KW - FCN

KW - fractional scaling

KW - fully convolutional layer

KW - fully convolutional network

KW - fully convolutional scaling

KW - pixelshuffle

KW - scaling

UR - http://www.scopus.com/inward/record.url?scp=85154033196&partnerID=8YFLogxK

U2 - 10.1109/SITIS57111.2022.00050

DO - 10.1109/SITIS57111.2022.00050

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85154033196

T3 - Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022

SP - 238

EP - 245

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

A2 - Yetongnon, Kokou

A2 - Dipanda, Albert

A2 - Gallo, Luigi

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 16th IEEE International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022

Y2 - 19 October 2022 through 21 October 2022

ER -

Soloveitchik M, Werman M. Fully Convolutional Fractional Scaling. In Yetongnon K, Dipanda A, Gallo L, editors, Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 238-245. (Proceedings - 16th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2022). doi: 10.1109/SITIS57111.2022.00050

Fully Convolutional Fractional Scaling

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this