VGGreNet: A Light-Weight VGGNet with Reused Convolutional Set

研究成果: Conference contribution同行評審

17 引文 斯高帕斯(Scopus)

摘要

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.

原文English
主出版物標題Proceedings - 2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing, UCC 2020
發行者Institute of Electrical and Electronics Engineers Inc.
頁面434-439
頁數6
ISBN(電子)9780738123943
DOIs
出版狀態Published - 12月 2020
事件13th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2020 - Virtual, Leicester, United Kingdom
持續時間: 7 12月 202010 12月 2020

出版系列

名字Proceedings - 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
國家/地區United Kingdom
城市Virtual, Leicester
期間7/12/2010/12/20

指紋

深入研究「VGGreNet: A Light-Weight VGGNet with Reused Convolutional Set」主題。共同形成了獨特的指紋。

引用此