VGGreNet: A Light-Weight VGGNet with Reused Convolutional Set

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

10 Citations (Scopus)

Abstract

This article introduces a light-weight VGGNet for deeper neural networks. In our model, we present a reusable convolution set that is designed to capture as much information as possible until the feature size is reduced to 1. The use of reusable layers for convolution can ensure the convergence without using a pre-trained model, and can greatly reduce the number of training parameters. Since these can be about 22.0% of the VGGNet, this leads to a reduction in memory consumption and faster convergence. As a result, the proposed model can improve the accuracy of testing. Moreover, the design and implementation can be easily deployed in the CNN approach related to the VGGNet model.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing, UCC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages434-439
Number of pages6
ISBN (Electronic)9780738123943
DOIs
Publication statusPublished - Dec 2020
Event13th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2020 - Virtual, Leicester, United Kingdom
Duration: 7 Dec 202010 Dec 2020

Publication series

NameProceedings - 2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing, UCC 2020

Conference

Conference13th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2020
Country/TerritoryUnited Kingdom
CityVirtual, Leicester
Period7/12/2010/12/20

Keywords

  • CNN
  • Deeper Neural Network
  • VGGNet

Fingerprint

Dive into the research topics of 'VGGreNet: A Light-Weight VGGNet with Reused Convolutional Set'. Together they form a unique fingerprint.

Cite this