利用 "学习 "结构光照的差分衍射网络进行高级图像分类

IF 6.5 1区 物理与天体物理 Q1 MATERIALS SCIENCE, MULTIDISCIPLINARY
Jiajun Zhang, Shuyan Zhang, Weijie Shi, Yong Hu, Zheng-Gao Dong, Jiaqi Li, Weibing Lu
{"title":"利用 \"学习 \"结构光照的差分衍射网络进行高级图像分类","authors":"Jiajun Zhang, Shuyan Zhang, Weijie Shi, Yong Hu, Zheng-Gao Dong, Jiaqi Li, Weibing Lu","doi":"10.1021/acsphotonics.4c01511","DOIUrl":null,"url":null,"abstract":"As a new optical machine learning framework, the diffractive deep neural network (D<sup>2</sup>NN) has attracted much attention due to its advantages such as low power consumption, parallel computing, and fast execution speed. Here, we demonstrate a new optical neural network design of a differential D<sup>2</sup>NN with structured illumination. In this scheme, the illumination patterns participate in the training process of the network and are optimized by an end-to-end technique. With the application of differential detection, the non-negativity constraint in a diffractive neural network can be alleviated. The test results show that this network architecture can achieve 97.63 and 88.10% classification accuracies on the MNIST and Fashion-MNIST data sets using only one diffractive layer, which exceeds the effect achieved by the five-layer traditional D<sup>2</sup>NN. Moreover, this network architecture can achieve a comprehensive improvement over a traditional D<sup>2</sup>NN in the challenging classification problems of tiny samples and samples blocked by occlusions. Compared with the traditional D<sup>2</sup>NN, this scheme innovatively uses the illumination patterns as new degrees of freedom in system design, which can effectively improve classification ability and reduce the space complexity of the optical neural network.","PeriodicalId":23,"journal":{"name":"ACS Photonics","volume":"57 1","pages":""},"PeriodicalIF":6.5000,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Advanced Image Classification Using a Differential Diffractive Network with “Learned” Structured Illumination\",\"authors\":\"Jiajun Zhang, Shuyan Zhang, Weijie Shi, Yong Hu, Zheng-Gao Dong, Jiaqi Li, Weibing Lu\",\"doi\":\"10.1021/acsphotonics.4c01511\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"As a new optical machine learning framework, the diffractive deep neural network (D<sup>2</sup>NN) has attracted much attention due to its advantages such as low power consumption, parallel computing, and fast execution speed. Here, we demonstrate a new optical neural network design of a differential D<sup>2</sup>NN with structured illumination. In this scheme, the illumination patterns participate in the training process of the network and are optimized by an end-to-end technique. With the application of differential detection, the non-negativity constraint in a diffractive neural network can be alleviated. The test results show that this network architecture can achieve 97.63 and 88.10% classification accuracies on the MNIST and Fashion-MNIST data sets using only one diffractive layer, which exceeds the effect achieved by the five-layer traditional D<sup>2</sup>NN. Moreover, this network architecture can achieve a comprehensive improvement over a traditional D<sup>2</sup>NN in the challenging classification problems of tiny samples and samples blocked by occlusions. Compared with the traditional D<sup>2</sup>NN, this scheme innovatively uses the illumination patterns as new degrees of freedom in system design, which can effectively improve classification ability and reduce the space complexity of the optical neural network.\",\"PeriodicalId\":23,\"journal\":{\"name\":\"ACS Photonics\",\"volume\":\"57 1\",\"pages\":\"\"},\"PeriodicalIF\":6.5000,\"publicationDate\":\"2024-11-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACS Photonics\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1021/acsphotonics.4c01511\",\"RegionNum\":1,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATERIALS SCIENCE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Photonics","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1021/acsphotonics.4c01511","RegionNum":1,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

作为一种新的光学机器学习框架,衍射深度神经网络(D2NN)因其低功耗、并行计算和执行速度快等优势而备受关注。在这里,我们展示了一种新的光学神经网络设计,即具有结构化照明的差分 D2NN。在该方案中,照明模式参与了网络的训练过程,并通过端到端技术进行了优化。通过差分检测的应用,可以缓解衍射神经网络中的非负约束。测试结果表明,该网络架构仅用一个衍射层就能在 MNIST 和 Fashion-MNIST 数据集上实现 97.63% 和 88.10% 的分类准确率,超过了五层传统 D2NN 所达到的效果。此外,在微小样本和样本被遮挡等具有挑战性的分类问题上,这种网络结构比传统的 D2NN 实现了全面的改进。与传统的 D2NN 相比,该方案创新性地将光照模式作为系统设计的新自由度,可有效提高分类能力,降低光神经网络的空间复杂度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Advanced Image Classification Using a Differential Diffractive Network with “Learned” Structured Illumination

Advanced Image Classification Using a Differential Diffractive Network with “Learned” Structured Illumination
As a new optical machine learning framework, the diffractive deep neural network (D2NN) has attracted much attention due to its advantages such as low power consumption, parallel computing, and fast execution speed. Here, we demonstrate a new optical neural network design of a differential D2NN with structured illumination. In this scheme, the illumination patterns participate in the training process of the network and are optimized by an end-to-end technique. With the application of differential detection, the non-negativity constraint in a diffractive neural network can be alleviated. The test results show that this network architecture can achieve 97.63 and 88.10% classification accuracies on the MNIST and Fashion-MNIST data sets using only one diffractive layer, which exceeds the effect achieved by the five-layer traditional D2NN. Moreover, this network architecture can achieve a comprehensive improvement over a traditional D2NN in the challenging classification problems of tiny samples and samples blocked by occlusions. Compared with the traditional D2NN, this scheme innovatively uses the illumination patterns as new degrees of freedom in system design, which can effectively improve classification ability and reduce the space complexity of the optical neural network.
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
ACS Photonics
ACS Photonics NANOSCIENCE & NANOTECHNOLOGY-MATERIALS SCIENCE, MULTIDISCIPLINARY
CiteScore
11.90
自引率
5.70%
发文量
438
审稿时长
2.3 months
期刊介绍: Published as soon as accepted and summarized in monthly issues, ACS Photonics will publish Research Articles, Letters, Perspectives, and Reviews, to encompass the full scope of published research in this field.
×
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