CAugment: An Approach to Diversifying Dataset by Combining Image Processing Operations

IF 2 4区 计算机科学 Q3 AUTOMATION & CONTROL SYSTEMS Information Technology and Control Pub Date : 2023-12-22 DOI:10.5755/j01.itc.52.4.33828
Wuliang Gao
{"title":"CAugment: An Approach to Diversifying Dataset by Combining Image Processing Operations","authors":"Wuliang Gao","doi":"10.5755/j01.itc.52.4.33828","DOIUrl":null,"url":null,"abstract":"In deep learning, model quality is extremely important. Consequently, the quality and the sufficiency of the datasets for training models have attracted considerable attention from both industry and academia. Automatic data augmentation, which provides a means of using image processing operators to generate data from existing datasets, is quite effective in searching for mutants of the images and expanding the training datasets. However, existing automatic data augmentation techniques often fail to fully exploit the potential of the data, failing to balance the search efficiency and the model accuracy. This paper presents CAugment, a novel approach to diversifying image datasets by combining image processing operators. Given a training image dataset, CAugment is composed of: 1) the three-level evolutionary algorithm (TLEA) that employs three levels of atomic operations for augmenting the dataset and an adaptive strategy for decreasing granularity and 2) a design that uses the three-dimensional evaluation method (TDEM) and a dHash algorithm to measure the diversity of the dataset. The search space can be expanded, which further improves model accuracy during training. We use CAugment to augment the CIFAR-10/100 and SVHN datasets and use the augmented datasets to train the WideResNet and Shake-Shake models. Our results show that the amount of data increases linearly along with the training epochs; in addition, the models trained by the CAugment-augmented datasets outperform those trained by the datasets augmented by the other techniques by up to 17.9% in accuracy on the SVHN dataset.","PeriodicalId":54982,"journal":{"name":"Information Technology and Control","volume":"58 4","pages":""},"PeriodicalIF":2.0000,"publicationDate":"2023-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information Technology and Control","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.5755/j01.itc.52.4.33828","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

In deep learning, model quality is extremely important. Consequently, the quality and the sufficiency of the datasets for training models have attracted considerable attention from both industry and academia. Automatic data augmentation, which provides a means of using image processing operators to generate data from existing datasets, is quite effective in searching for mutants of the images and expanding the training datasets. However, existing automatic data augmentation techniques often fail to fully exploit the potential of the data, failing to balance the search efficiency and the model accuracy. This paper presents CAugment, a novel approach to diversifying image datasets by combining image processing operators. Given a training image dataset, CAugment is composed of: 1) the three-level evolutionary algorithm (TLEA) that employs three levels of atomic operations for augmenting the dataset and an adaptive strategy for decreasing granularity and 2) a design that uses the three-dimensional evaluation method (TDEM) and a dHash algorithm to measure the diversity of the dataset. The search space can be expanded, which further improves model accuracy during training. We use CAugment to augment the CIFAR-10/100 and SVHN datasets and use the augmented datasets to train the WideResNet and Shake-Shake models. Our results show that the amount of data increases linearly along with the training epochs; in addition, the models trained by the CAugment-augmented datasets outperform those trained by the datasets augmented by the other techniques by up to 17.9% in accuracy on the SVHN dataset.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
CAugment:通过组合图像处理操作实现数据集多样化的方法
在深度学习中,模型质量极为重要。因此,用于训练模型的数据集的质量和充足性引起了业界和学术界的极大关注。自动数据扩增提供了一种使用图像处理算子从现有数据集生成数据的方法,在搜索图像突变体和扩展训练数据集方面相当有效。然而,现有的自动数据扩增技术往往不能充分挖掘数据的潜力,无法兼顾搜索效率和模型准确性。本文介绍的 CAugment 是一种通过结合图像处理算子实现图像数据集多样化的新方法。给定一个训练图像数据集,CAugment 由以下部分组成:1) 三级进化算法(TLEA),该算法采用三级原子运算来增强数据集,并采用自适应策略来降低粒度;以及 2) 使用三维评估方法(TDEM)和 dHash 算法来衡量数据集多样性的设计。搜索空间可以扩展,从而在训练过程中进一步提高模型的准确性。我们使用 CAugment 来增强 CIFAR-10/100 和 SVHN 数据集,并使用增强后的数据集来训练 WideResNet 和 Shake-Shake 模型。我们的结果表明,数据量与训练历时呈线性增长;此外,在 SVHN 数据集上,由 CAugment 扩增的数据集所训练的模型比由其他技术扩增的数据集所训练的模型准确率高出 17.9%。
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 去求助
来源期刊
Information Technology and Control
Information Technology and Control 工程技术-计算机:人工智能
CiteScore
2.70
自引率
9.10%
发文量
36
审稿时长
12 months
期刊介绍: Periodical journal covers a wide field of computer science and control systems related problems including: -Software and hardware engineering; -Management systems engineering; -Information systems and databases; -Embedded systems; -Physical systems modelling and application; -Computer networks and cloud computing; -Data visualization; -Human-computer interface; -Computer graphics, visual analytics, and multimedia systems.
期刊最新文献
Model construction of big data asset management system for digital power grid regulation Melanoma Diagnosis Using Enhanced Faster Region Convolutional Neural Networks Optimized by Artificial Gorilla Troops Algorithm A Scalable and Stacked Ensemble Approach to Improve Intrusion Detection in Clouds Traffic Sign Detection Algorithm Based on Improved Yolox Apply Physical System Model and Computer Algorithm to Identify Osmanthus Fragrans Seed Vigor Based on Hyperspectral Imaging and Convolutional Neural Network
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1