Efficient Pyramid-Structured Networks Using Channel Separating Gate

Yoon Jae Yeo, Min Cheol Sagong, Sung Jea Ko, Dong Pan Lim

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

    Abstract

    Convolutional neural networks (CNNs) have been brought noticeable improvement on numerous image processing applications. In particular, spatial pyramid structures have been widely used, but the number of required parameters increases exponentially as the network deepens. Therefore, we propose a channel separating gate (CSG) that can determine the number of channels in convolutional layers according to the spatial level. For a given spatial level, the CSG separates the channels of feature maps for use at the smaller level. Consequently, the standard non- pooling model can be altered to an efficient pyramid structure by performing the proposed method repeatedly. For single image super-resolution (SR) and deblurring, we demonstrate that our method improves the baseline network in terms of peak signal- to-noise ratio (PSNR) and floating-point operations (FLOPs).

    Original languageEnglish
    Title of host publication2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages986-987
    Number of pages2
    ISBN (Electronic)9781665436762
    DOIs
    Publication statusPublished - 2021
    Event10th IEEE Global Conference on Consumer Electronics, GCCE 2021 - Kyoto, Japan
    Duration: 2021 Oct 122021 Oct 15

    Publication series

    Name2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021

    Conference

    Conference10th IEEE Global Conference on Consumer Electronics, GCCE 2021
    Country/TerritoryJapan
    CityKyoto
    Period21/10/1221/10/15

    Bibliographical note

    Publisher Copyright:
    © 2021 IEEE.

    Keywords

    • convolutional neural network (CNN)
    • deblurring
    • pyramid structure
    • super-resolution (SR)

    ASJC Scopus subject areas

    • Computer Science Applications
    • Signal Processing
    • Biomedical Engineering
    • Electrical and Electronic Engineering
    • Media Technology
    • Instrumentation

    Fingerprint

    Dive into the research topics of 'Efficient Pyramid-Structured Networks Using Channel Separating Gate'. Together they form a unique fingerprint.

    Cite this