SLADS-Net:基于深度神经网络的动态采样监督学习方法

Yan Zhang, G. Godaliyadda, N. Ferrier, E. Gulsoy, C. Bouman, C. Phatak
{"title":"SLADS-Net:基于深度神经网络的动态采样监督学习方法","authors":"Yan Zhang, G. Godaliyadda, N. Ferrier, E. Gulsoy, C. Bouman, C. Phatak","doi":"10.2352/ISSN.2470-1173.2018.15.COIMG-131","DOIUrl":null,"url":null,"abstract":"In scanning microscopy based imaging techniques, there is a need to develop novel data acquisition schemes that can reduce the time for data acquisition and minimize sample exposure to the probing radiation. Sparse sampling schemes are ideally suited for such applications where the images can be reconstructed from a sparse set of measurements. In particular, dynamic sparse sampling based on supervised learning has shown promising results for practical applications. However, a particular drawback of such methods is that it requires training image sets with similar information content which may not always be available. In this paper, we introduce a Supervised Learning Approach for Dynamic Sampling (SLADS) algorithm that uses a deep neural network based training approach. We call this algorithm SLADS- Net. We have performed simulated experiments for dynamic sampling using SLADS-Net in which the training images either have similar information content or completely different information content, when compared to the testing images. We compare the performance across various methods for training such as least- squares, support vector regression and deep neural networks. From these results we observe that deep neural network based training results in superior performance when the training and testing images are not similar. We also discuss the development of a pre-trained SLADS-Net that uses generic images for training. Here, the neural network parameters are pre-trained so that users can directly apply SLADS-Net for imaging experiments.","PeriodicalId":8487,"journal":{"name":"arXiv: Signal Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"13","resultStr":"{\"title\":\"SLADS-Net: Supervised Learning Approach for Dynamic Sampling using Deep Neural Networks\",\"authors\":\"Yan Zhang, G. Godaliyadda, N. Ferrier, E. Gulsoy, C. Bouman, C. Phatak\",\"doi\":\"10.2352/ISSN.2470-1173.2018.15.COIMG-131\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In scanning microscopy based imaging techniques, there is a need to develop novel data acquisition schemes that can reduce the time for data acquisition and minimize sample exposure to the probing radiation. Sparse sampling schemes are ideally suited for such applications where the images can be reconstructed from a sparse set of measurements. In particular, dynamic sparse sampling based on supervised learning has shown promising results for practical applications. However, a particular drawback of such methods is that it requires training image sets with similar information content which may not always be available. In this paper, we introduce a Supervised Learning Approach for Dynamic Sampling (SLADS) algorithm that uses a deep neural network based training approach. We call this algorithm SLADS- Net. We have performed simulated experiments for dynamic sampling using SLADS-Net in which the training images either have similar information content or completely different information content, when compared to the testing images. We compare the performance across various methods for training such as least- squares, support vector regression and deep neural networks. From these results we observe that deep neural network based training results in superior performance when the training and testing images are not similar. We also discuss the development of a pre-trained SLADS-Net that uses generic images for training. Here, the neural network parameters are pre-trained so that users can directly apply SLADS-Net for imaging experiments.\",\"PeriodicalId\":8487,\"journal\":{\"name\":\"arXiv: Signal Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-03-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"13\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv: Signal Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2352/ISSN.2470-1173.2018.15.COIMG-131\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv: Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2352/ISSN.2470-1173.2018.15.COIMG-131","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 13

摘要

在基于扫描显微镜的成像技术中,需要开发新的数据采集方案,以减少数据采集时间并最大限度地减少样品暴露于探测辐射。稀疏采样方案非常适合这样的应用,其中图像可以从一个稀疏的测量集重建。特别是基于监督学习的动态稀疏采样在实际应用中表现出了良好的效果。然而,这种方法的一个特别缺点是它需要具有相似信息内容的训练图像集,而这些信息内容可能并不总是可用的。在本文中,我们介绍了一种基于深度神经网络的训练方法的动态采样(SLADS)算法的监督学习方法。我们称这种算法为SLADS- Net。我们使用SLADS-Net进行了动态采样的模拟实验,其中训练图像与测试图像相比,要么具有相似的信息内容,要么具有完全不同的信息内容。我们比较了各种训练方法的性能,如最小二乘、支持向量回归和深度神经网络。从这些结果中我们观察到,当训练图像和测试图像不相似时,基于深度神经网络的训练效果更好。我们还讨论了使用通用图像进行训练的预训练SLADS-Net的开发。在这里,对神经网络参数进行预训练,使用户可以直接应用SLADS-Net进行成像实验。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
SLADS-Net: Supervised Learning Approach for Dynamic Sampling using Deep Neural Networks
In scanning microscopy based imaging techniques, there is a need to develop novel data acquisition schemes that can reduce the time for data acquisition and minimize sample exposure to the probing radiation. Sparse sampling schemes are ideally suited for such applications where the images can be reconstructed from a sparse set of measurements. In particular, dynamic sparse sampling based on supervised learning has shown promising results for practical applications. However, a particular drawback of such methods is that it requires training image sets with similar information content which may not always be available. In this paper, we introduce a Supervised Learning Approach for Dynamic Sampling (SLADS) algorithm that uses a deep neural network based training approach. We call this algorithm SLADS- Net. We have performed simulated experiments for dynamic sampling using SLADS-Net in which the training images either have similar information content or completely different information content, when compared to the testing images. We compare the performance across various methods for training such as least- squares, support vector regression and deep neural networks. From these results we observe that deep neural network based training results in superior performance when the training and testing images are not similar. We also discuss the development of a pre-trained SLADS-Net that uses generic images for training. Here, the neural network parameters are pre-trained so that users can directly apply SLADS-Net for imaging experiments.
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
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