CMVT: ConVit Transformer Network Recombined with Convolutional Layer

IF 0.8 Q4 COMPUTER SCIENCE, SOFTWARE ENGINEERING
Chunxia Mao, Jun Li, Tao Hu, Xu Zhao
{"title":"CMVT: ConVit Transformer Network Recombined with Convolutional Layer","authors":"Chunxia Mao, Jun Li, Tao Hu, Xu Zhao","doi":"10.1142/s0219467824500608","DOIUrl":null,"url":null,"abstract":"Vision transformers are deep neural networks applied to image classification based on a self-attention mechanism and can process data in parallel. Aiming at the structural loss of Vision transformers, this paper combines ConViT and Convolutional Neural Network (CNN) and proposes a new model Convolution Meet Vision Transformers (CMVT). This model adds a convolution module to the ConViT network to solve the structural loss of the transformer. By adding hierarchical data representation, the ability to gradually extract more image classification features is improved. We have conducted comparative experiments on multiple dataset, and all of them have been enhanced to improve the efficiency and performance of the model.","PeriodicalId":44688,"journal":{"name":"International Journal of Image and Graphics","volume":null,"pages":null},"PeriodicalIF":0.8000,"publicationDate":"2024-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Image and Graphics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1142/s0219467824500608","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0

Abstract

Vision transformers are deep neural networks applied to image classification based on a self-attention mechanism and can process data in parallel. Aiming at the structural loss of Vision transformers, this paper combines ConViT and Convolutional Neural Network (CNN) and proposes a new model Convolution Meet Vision Transformers (CMVT). This model adds a convolution module to the ConViT network to solve the structural loss of the transformer. By adding hierarchical data representation, the ability to gradually extract more image classification features is improved. We have conducted comparative experiments on multiple dataset, and all of them have been enhanced to improve the efficiency and performance of the model.
CMVT:与卷积层重组的 ConVit Transformer 网络
视觉变换器是一种基于自我注意机制的深度神经网络,可并行处理数据,适用于图像分类。针对视觉变换器的结构损失问题,本文将 ConViT 与卷积神经网络(CNN)相结合,提出了一种新模型 Convolution Meet Vision Transformers(CMVT)。该模型在 ConViT 网络中增加了一个卷积模块,以解决变压器的结构损失问题。通过添加分层数据表示,逐步提取更多图像分类特征的能力得到了提高。我们在多个数据集上进行了对比实验,所有数据集都得到了增强,从而提高了模型的效率和性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
International Journal of Image and Graphics
International Journal of Image and Graphics COMPUTER SCIENCE, SOFTWARE ENGINEERING-
CiteScore
2.40
自引率
18.80%
发文量
67
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信