Robustness enhancement in neural networks with alpha-stable training noise

IF 2.9 3区 工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC Digital Signal Processing Pub Date : 2024-09-20 DOI:10.1016/j.dsp.2024.104778
Xueqiong Yuan , Jipeng Li , Ercan Engin Kuruoglu
{"title":"Robustness enhancement in neural networks with alpha-stable training noise","authors":"Xueqiong Yuan ,&nbsp;Jipeng Li ,&nbsp;Ercan Engin Kuruoglu","doi":"10.1016/j.dsp.2024.104778","DOIUrl":null,"url":null,"abstract":"<div><div>With the increasing use of deep learning on data collected by non-perfect sensors and in non-perfect environments, the robustness of deep learning systems has become an important issue. A common approach for obtaining robustness to noise has been to train deep learning systems with data augmented with Gaussian noise. In this work, the common choice of Gaussian noise is challenged and the possibility of stronger robustness for non-Gaussian impulsive noise is explored, specifically alpha-stable noise. Justified by the Generalized Central Limit Theorem and evidenced by observations in various application areas, alpha-stable noise is widely present in nature. By comparing the testing accuracy of models trained with Gaussian noise and alpha-stable noise on data corrupted by different noise, it is found that training with alpha-stable noise is more effective than Gaussian noise, especially when the dataset is corrupted by impulsive noise, thus improving the robustness of the model. Moreover, in the testing on the common corruption benchmark dataset, training with alpha-stable noise also achieves promising results, improving the robustness of the model to other corruption types and demonstrating comparable performance with other state-of-the-art data augmentation methods. Consequently, a novel data augmentation method is proposed that replaces Gaussian noise, which is typically added to the training data, with alpha-stable noise.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"156 ","pages":"Article 104778"},"PeriodicalIF":2.9000,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Digital Signal Processing","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1051200424004032","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

With the increasing use of deep learning on data collected by non-perfect sensors and in non-perfect environments, the robustness of deep learning systems has become an important issue. A common approach for obtaining robustness to noise has been to train deep learning systems with data augmented with Gaussian noise. In this work, the common choice of Gaussian noise is challenged and the possibility of stronger robustness for non-Gaussian impulsive noise is explored, specifically alpha-stable noise. Justified by the Generalized Central Limit Theorem and evidenced by observations in various application areas, alpha-stable noise is widely present in nature. By comparing the testing accuracy of models trained with Gaussian noise and alpha-stable noise on data corrupted by different noise, it is found that training with alpha-stable noise is more effective than Gaussian noise, especially when the dataset is corrupted by impulsive noise, thus improving the robustness of the model. Moreover, in the testing on the common corruption benchmark dataset, training with alpha-stable noise also achieves promising results, improving the robustness of the model to other corruption types and demonstrating comparable performance with other state-of-the-art data augmentation methods. Consequently, a novel data augmentation method is proposed that replaces Gaussian noise, which is typically added to the training data, with alpha-stable noise.
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
利用阿尔法稳定训练噪声增强神经网络的鲁棒性
随着深度学习越来越多地用于非完美传感器和非完美环境中收集的数据,深度学习系统的鲁棒性已成为一个重要问题。获得噪声鲁棒性的一种常见方法是用添加了高斯噪声的数据训练深度学习系统。在这项工作中,人们对高斯噪声的常见选择提出了质疑,并探索了非高斯脉冲噪声(特别是阿尔法稳定噪声)具有更强鲁棒性的可能性。根据广义中心极限定理,并通过在不同应用领域的观察证明,α-稳定噪声广泛存在于自然界中。通过比较用高斯噪声和阿尔法稳定噪声训练的模型在不同噪声破坏的数据上的测试精度,发现用阿尔法稳定噪声训练比高斯噪声更有效,特别是当数据集被脉冲噪声破坏时,从而提高了模型的鲁棒性。此外,在对常见腐败基准数据集进行测试时,使用阿尔法稳定噪声进行训练也取得了可喜的结果,提高了模型对其他腐败类型的鲁棒性,其性能与其他最先进的数据增强方法不相上下。因此,我们提出了一种新的数据增强方法,用阿尔法稳定噪声取代通常添加到训练数据中的高斯噪声。
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
Digital Signal Processing
Digital Signal Processing 工程技术-工程:电子与电气
CiteScore
5.30
自引率
17.20%
发文量
435
审稿时长
66 days
期刊介绍: Digital Signal Processing: A Review Journal is one of the oldest and most established journals in the field of signal processing yet it aims to be the most innovative. The Journal invites top quality research articles at the frontiers of research in all aspects of signal processing. Our objective is to provide a platform for the publication of ground-breaking research in signal processing with both academic and industrial appeal. The journal has a special emphasis on statistical signal processing methodology such as Bayesian signal processing, and encourages articles on emerging applications of signal processing such as: • big data• machine learning• internet of things• information security• systems biology and computational biology,• financial time series analysis,• autonomous vehicles,• quantum computing,• neuromorphic engineering,• human-computer interaction and intelligent user interfaces,• environmental signal processing,• geophysical signal processing including seismic signal processing,• chemioinformatics and bioinformatics,• audio, visual and performance arts,• disaster management and prevention,• renewable energy,
期刊最新文献
Adaptive polarimetric persymmetric detection for distributed subspace targets in lognormal texture clutter MFFR-net: Multi-scale feature fusion and attentive recalibration network for deep neural speech enhancement PV-YOLO: A lightweight pedestrian and vehicle detection model based on improved YOLOv8 Efficient recurrent real video restoration IGGCN: Individual-guided graph convolution network for pedestrian trajectory prediction
×
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