基于因子分析的神经网络图像分类器

IF 0.5 4区 数学 Q3 MATHEMATICS
A. M. Dostovalova, A. K. Gorshenin
{"title":"基于因子分析的神经网络图像分类器","authors":"A. M. Dostovalova,&nbsp;A. K. Gorshenin","doi":"10.1134/S106456242460204X","DOIUrl":null,"url":null,"abstract":"<p>The paper develops an approach to probability informing deep neural networks, that is, improving their results by using various probability models within architectural elements. We introduce factor analyzers with additive and impulse noise components as such models. The identifiability of the model is proved. The relationship between the parameter estimates by the methods of least squares and maximum likelihood is established, which actually means that the estimates of the parameters of the factor analyzer obtained within the informed block are unbiased and consistent. A mathematical model is used to create a new architectural element that implements the fusion of multiscale image features to improve classification accuracy in the case of a small volume of training data. This problem is typical for various applied tasks, including remote sensing data analysis. Various widely used neural network classifiers (EfficientNet, MobileNet, and Xception), both with and without a new informed block, are tested. It is demonstrated that on the open datasets UC Merced (remote sensing data) and Oxford Flowers (flower images), informed neural networks achieve a significant increase in accuracy for this class of tasks: the largest improvement in Top-1 accuracy was 6.67% (mean accuracy without informing equals 87.3%), while Top-5 accuracy increased by 1.49% (mean base accuracy value is 96.27%).</p>","PeriodicalId":531,"journal":{"name":"Doklady Mathematics","volume":"110 1 supplement","pages":"S35 - S41"},"PeriodicalIF":0.5000,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1134/S106456242460204X.pdf","citationCount":"0","resultStr":"{\"title\":\"Neural Network Image Classifiers Informed by Factor Analyzers\",\"authors\":\"A. M. Dostovalova,&nbsp;A. K. Gorshenin\",\"doi\":\"10.1134/S106456242460204X\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The paper develops an approach to probability informing deep neural networks, that is, improving their results by using various probability models within architectural elements. We introduce factor analyzers with additive and impulse noise components as such models. The identifiability of the model is proved. The relationship between the parameter estimates by the methods of least squares and maximum likelihood is established, which actually means that the estimates of the parameters of the factor analyzer obtained within the informed block are unbiased and consistent. A mathematical model is used to create a new architectural element that implements the fusion of multiscale image features to improve classification accuracy in the case of a small volume of training data. This problem is typical for various applied tasks, including remote sensing data analysis. Various widely used neural network classifiers (EfficientNet, MobileNet, and Xception), both with and without a new informed block, are tested. It is demonstrated that on the open datasets UC Merced (remote sensing data) and Oxford Flowers (flower images), informed neural networks achieve a significant increase in accuracy for this class of tasks: the largest improvement in Top-1 accuracy was 6.67% (mean accuracy without informing equals 87.3%), while Top-5 accuracy increased by 1.49% (mean base accuracy value is 96.27%).</p>\",\"PeriodicalId\":531,\"journal\":{\"name\":\"Doklady Mathematics\",\"volume\":\"110 1 supplement\",\"pages\":\"S35 - S41\"},\"PeriodicalIF\":0.5000,\"publicationDate\":\"2025-03-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://link.springer.com/content/pdf/10.1134/S106456242460204X.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Doklady Mathematics\",\"FirstCategoryId\":\"100\",\"ListUrlMain\":\"https://link.springer.com/article/10.1134/S106456242460204X\",\"RegionNum\":4,\"RegionCategory\":\"数学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"MATHEMATICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Doklady Mathematics","FirstCategoryId":"100","ListUrlMain":"https://link.springer.com/article/10.1134/S106456242460204X","RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MATHEMATICS","Score":null,"Total":0}
引用次数: 0

摘要

本文开发了一种概率通知深度神经网络的方法,即通过在架构元素中使用各种概率模型来改进其结果。我们介绍了以加性和脉冲噪声成分为模型的因子分析仪。证明了模型的可辨识性。建立了最小二乘法和最大似然法的参数估计之间的关系,这实际上意味着在知情块内得到的因子分析仪的参数估计是无偏和一致的。利用数学模型创建新的架构元素,实现多尺度图像特征的融合,在训练数据量小的情况下提高分类精度。这个问题是各种应用任务的典型问题,包括遥感数据分析。测试了各种广泛使用的神经网络分类器(EfficientNet, MobileNet和Xception),无论是否有新的通知块。结果表明,在开放数据集UC Merced(遥感数据)和Oxford Flowers(花卉图像)上,知情神经网络在这类任务上的准确率显著提高:Top-1的准确率最大提高了6.67%(未告知的平均准确率为87.3%),Top-5的准确率提高了1.49%(平均基础准确率值为96.27%)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Neural Network Image Classifiers Informed by Factor Analyzers

The paper develops an approach to probability informing deep neural networks, that is, improving their results by using various probability models within architectural elements. We introduce factor analyzers with additive and impulse noise components as such models. The identifiability of the model is proved. The relationship between the parameter estimates by the methods of least squares and maximum likelihood is established, which actually means that the estimates of the parameters of the factor analyzer obtained within the informed block are unbiased and consistent. A mathematical model is used to create a new architectural element that implements the fusion of multiscale image features to improve classification accuracy in the case of a small volume of training data. This problem is typical for various applied tasks, including remote sensing data analysis. Various widely used neural network classifiers (EfficientNet, MobileNet, and Xception), both with and without a new informed block, are tested. It is demonstrated that on the open datasets UC Merced (remote sensing data) and Oxford Flowers (flower images), informed neural networks achieve a significant increase in accuracy for this class of tasks: the largest improvement in Top-1 accuracy was 6.67% (mean accuracy without informing equals 87.3%), while Top-5 accuracy increased by 1.49% (mean base accuracy value is 96.27%).

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Doklady Mathematics
Doklady Mathematics 数学-数学
CiteScore
1.00
自引率
16.70%
发文量
39
审稿时长
3-6 weeks
期刊介绍: Doklady Mathematics is a journal of the Presidium of the Russian Academy of Sciences. It contains English translations of papers published in Doklady Akademii Nauk (Proceedings of the Russian Academy of Sciences), which was founded in 1933 and is published 36 times a year. Doklady Mathematics includes the materials from the following areas: mathematics, mathematical physics, computer science, control theory, and computers. It publishes brief scientific reports on previously unpublished significant new research in mathematics and its applications. The main contributors to the journal are Members of the RAS, Corresponding Members of the RAS, and scientists from the former Soviet Union and other foreign countries. Among the contributors are the outstanding Russian mathematicians.
×
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