CNN filter sizes, effects, limitations, and challenges: An exploratory study.

Mohamed Aboukhair, Fahad Alsheref, Adel Assiri, Abdelrahim Koura, Mohammed Kayed
{"title":"CNN filter sizes, effects, limitations, and challenges: An exploratory study.","authors":"Mohamed Aboukhair, Fahad Alsheref, Adel Assiri, Abdelrahim Koura, Mohammed Kayed","doi":"10.1080/0954898X.2025.2533865","DOIUrl":null,"url":null,"abstract":"<p><p>This study explores the impacts of filter sizes on convolutional neural networks (CNNs) models, moving away from the common belief that small filters (3x3) give better results. The goal is to highlight the potential of large filters and encourage researchers to investigate their capabilities. The usage of large filters will increase the computational power which leads common researchers to reduce the filter size to reserve this power; however, other researchers address the potential of large filters to enhance the performance of CNN models. Currently, there are few pure CNN models that achieve optimal performance with large filters showing how far the large filter sizes topic is not addressed well by the community. As the availability of computer power and image sizes increase, traditional obstacles that hinder researchers from using large filter sizes will gradually diminish. This paper guides researchers by analysing and exploring the limitations, challenges, and impacts of CNN filter sizes on different CNN architectures. This will help utilize large filters' distinctive opportunities and potential. To our knowledge, we find four opportunities from utilizing large filters. A comprehensive comparison of researches on different CNN architectures shows a bias for small filters (3x3) and the possible potential of large filters.</p>","PeriodicalId":520718,"journal":{"name":"Network (Bristol, England)","volume":" ","pages":"1-29"},"PeriodicalIF":0.0000,"publicationDate":"2025-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Network (Bristol, England)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/0954898X.2025.2533865","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

This study explores the impacts of filter sizes on convolutional neural networks (CNNs) models, moving away from the common belief that small filters (3x3) give better results. The goal is to highlight the potential of large filters and encourage researchers to investigate their capabilities. The usage of large filters will increase the computational power which leads common researchers to reduce the filter size to reserve this power; however, other researchers address the potential of large filters to enhance the performance of CNN models. Currently, there are few pure CNN models that achieve optimal performance with large filters showing how far the large filter sizes topic is not addressed well by the community. As the availability of computer power and image sizes increase, traditional obstacles that hinder researchers from using large filter sizes will gradually diminish. This paper guides researchers by analysing and exploring the limitations, challenges, and impacts of CNN filter sizes on different CNN architectures. This will help utilize large filters' distinctive opportunities and potential. To our knowledge, we find four opportunities from utilizing large filters. A comprehensive comparison of researches on different CNN architectures shows a bias for small filters (3x3) and the possible potential of large filters.

CNN过滤器的大小、效果、限制和挑战:一项探索性研究。
本研究探讨了过滤器大小对卷积神经网络(cnn)模型的影响,摆脱了人们普遍认为的小过滤器(3x3)会产生更好的结果。目的是突出大型过滤器的潜力,并鼓励研究人员调查它们的能力。大型滤波器的使用将增加计算能力,这导致一般研究人员减小滤波器尺寸以保留计算能力;然而,其他研究人员解决了大型过滤器的潜力,以提高CNN模型的性能。目前,很少有纯CNN模型在使用大过滤器的情况下达到最佳性能,这表明社区在很大程度上没有很好地解决大过滤器尺寸的问题。随着计算机能力和图像尺寸的增加,阻碍研究人员使用大尺寸滤波器的传统障碍将逐渐减少。本文通过分析和探索CNN滤波器尺寸对不同CNN架构的限制、挑战和影响来指导研究人员。这将有助于利用大型过滤器的独特机会和潜力。据我们所知,我们发现使用大型过滤器有四个机会。对不同CNN架构的研究进行全面比较,可以看出小滤波器(3 × 3)和大滤波器的潜力。
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
自引率
0.00%
发文量
0
×
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:604180095
Book学术官方微信