COMPARISON OF VISION TRANSFORMERS AND CONVOLUTIONAL NEURAL NETWORKS FOR SKIN DISEASE CLASSIFICATION

Muhammet Fatih Aslan
{"title":"COMPARISON OF VISION TRANSFORMERS AND CONVOLUTIONAL NEURAL NETWORKS FOR SKIN DISEASE CLASSIFICATION","authors":"Muhammet Fatih Aslan","doi":"10.58190/icontas.2023.51","DOIUrl":null,"url":null,"abstract":"Skin diseases are one of the most common diseases in humans. Due to its many various symptoms and types, computer vision studies have been frequently applied to its diagnosis and classification. Previous studies have frequently used machine learning methods and deep learning-based Convolutional Neural Networks (CNN) for skin disease diagnosis. Although deep learning-based applications have achieved great success in terms of detection accuracy, research continues to ensure the desired performance. However, Vision Transformer (ViT), recently proposed as a competitive alternative to CNNs, is gaining increasing popularity. This paper compares ResNet18 and ResNet50 networks, important CNN models, with ViT for classifying skin disease. The comparison is applied on a dataset containing a small number of samples. In the application performed on a dataset containing skin disease images, ViT provides 68.93% classification accuracy, while ResNet18 and ResNet50 classification accuracy is 61.65% and 61.17%, respectively. Other metrics calculated along with the accuracies also prove the superiority of ViT over ResNet models. However, ViT has a big disadvantage in terms of training time.","PeriodicalId":509439,"journal":{"name":"Proceedings of the International Conference on New Trends in Applied Sciences","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the International Conference on New Trends in Applied Sciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.58190/icontas.2023.51","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

Skin diseases are one of the most common diseases in humans. Due to its many various symptoms and types, computer vision studies have been frequently applied to its diagnosis and classification. Previous studies have frequently used machine learning methods and deep learning-based Convolutional Neural Networks (CNN) for skin disease diagnosis. Although deep learning-based applications have achieved great success in terms of detection accuracy, research continues to ensure the desired performance. However, Vision Transformer (ViT), recently proposed as a competitive alternative to CNNs, is gaining increasing popularity. This paper compares ResNet18 and ResNet50 networks, important CNN models, with ViT for classifying skin disease. The comparison is applied on a dataset containing a small number of samples. In the application performed on a dataset containing skin disease images, ViT provides 68.93% classification accuracy, while ResNet18 and ResNet50 classification accuracy is 61.65% and 61.17%, respectively. Other metrics calculated along with the accuracies also prove the superiority of ViT over ResNet models. However, ViT has a big disadvantage in terms of training time.
比较视觉变换器和卷积神经网络在皮肤病分类中的应用
皮肤病是人类最常见的疾病之一。由于皮肤病的症状和类型多种多样,计算机视觉研究经常被应用于皮肤病的诊断和分类。以往的研究经常将机器学习方法和基于深度学习的卷积神经网络(CNN)用于皮肤病诊断。虽然基于深度学习的应用在检测准确性方面取得了巨大成功,但为确保达到预期性能,研究仍在继续。然而,最近作为 CNN 的竞争性替代品而提出的视觉变换器(ViT)正日益受到欢迎。本文将重要的 CNN 模型 ResNet18 和 ResNet50 网络与 ViT 在皮肤病分类方面进行了比较。比较是在包含少量样本的数据集上进行的。在对包含皮肤病图像的数据集进行的应用中,ViT 的分类准确率为 68.93%,而 ResNet18 和 ResNet50 的分类准确率分别为 61.65% 和 61.17%。与准确率一起计算的其他指标也证明了 ViT 优于 ResNet 模型。不过,ViT 在训练时间方面有很大的劣势。
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:481959085
Book学术官方微信