天体点源图像分类的多模态迁移学习方法

IF 3.3 3区 物理与天体物理 Q2 ASTRONOMY & ASTROPHYSICS
Bingjun Wang, Shuxin Hong, Zhiyang Yuan, A-Li Luo, Xiao Kong, Zhiqiang Zou
{"title":"天体点源图像分类的多模态迁移学习方法","authors":"Bingjun Wang, Shuxin Hong, Zhiyang Yuan, A-Li Luo, Xiao Kong, Zhiqiang Zou","doi":"10.1088/1538-3873/acfbb9","DOIUrl":null,"url":null,"abstract":"Abstract A large fraction of celestial objects exhibit point shapes in CCD images, such as stars and QSOs, which contain less information due to their few pixels. Point source classification based solely on image data may lead to low accuracy. To address this challenge, this paper proposes a Multi-modal Transfer Learning-based classification method for celestial objects with point shape images. Considering that spectral data possess rich features and that there is a correlation between spectral data and image data, the proposed approach fully utilizes the knowledge gained from celestial spectral data and transfers it to the original image-based classification, enhancing the accuracy of classifying stars and QSOs. Initially, a one-dimensional residual network is employed to extract a 128-dimensional spectral feature vector from the original 3700-dimensional spectral data. This spectral feature vector captures important features of the celestial object. The Generative Adversarial Network is then utilized to generate a simulated spectral vector of 128 dimensions, which corresponds to the celestial object image. By generating simulated spectral vectors, data from two modals (spectral and image) for the same celestial object are available, enriching the input features of the model. In the upcoming multimodal classification model, we only require the images of celestial objects along with their corresponding simulated spectral data, and we no longer need real spectral data. With the assistance of spectral data, the proposed method alleviates the above disadvantages of the original image-based classification method. Remarkably, our method has improved the F1-score from 0.93 to 0.9777, while reducing the error rate in classification by 40%. These enhancements significantly increase the classification accuracy of stars and QSOs, providing strong support for the classification of celestial point sources.","PeriodicalId":20820,"journal":{"name":"Publications of the Astronomical Society of the Pacific","volume":"17 1","pages":"0"},"PeriodicalIF":3.3000,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Multimodal Transfer Learning Method for Classifying Images of Celestial Point Sources\",\"authors\":\"Bingjun Wang, Shuxin Hong, Zhiyang Yuan, A-Li Luo, Xiao Kong, Zhiqiang Zou\",\"doi\":\"10.1088/1538-3873/acfbb9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract A large fraction of celestial objects exhibit point shapes in CCD images, such as stars and QSOs, which contain less information due to their few pixels. Point source classification based solely on image data may lead to low accuracy. To address this challenge, this paper proposes a Multi-modal Transfer Learning-based classification method for celestial objects with point shape images. Considering that spectral data possess rich features and that there is a correlation between spectral data and image data, the proposed approach fully utilizes the knowledge gained from celestial spectral data and transfers it to the original image-based classification, enhancing the accuracy of classifying stars and QSOs. Initially, a one-dimensional residual network is employed to extract a 128-dimensional spectral feature vector from the original 3700-dimensional spectral data. This spectral feature vector captures important features of the celestial object. The Generative Adversarial Network is then utilized to generate a simulated spectral vector of 128 dimensions, which corresponds to the celestial object image. By generating simulated spectral vectors, data from two modals (spectral and image) for the same celestial object are available, enriching the input features of the model. In the upcoming multimodal classification model, we only require the images of celestial objects along with their corresponding simulated spectral data, and we no longer need real spectral data. With the assistance of spectral data, the proposed method alleviates the above disadvantages of the original image-based classification method. Remarkably, our method has improved the F1-score from 0.93 to 0.9777, while reducing the error rate in classification by 40%. These enhancements significantly increase the classification accuracy of stars and QSOs, providing strong support for the classification of celestial point sources.\",\"PeriodicalId\":20820,\"journal\":{\"name\":\"Publications of the Astronomical Society of the Pacific\",\"volume\":\"17 1\",\"pages\":\"0\"},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2023-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Publications of the Astronomical Society of the Pacific\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1088/1538-3873/acfbb9\",\"RegionNum\":3,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ASTRONOMY & ASTROPHYSICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Publications of the Astronomical Society of the Pacific","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1088/1538-3873/acfbb9","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ASTRONOMY & ASTROPHYSICS","Score":null,"Total":0}
引用次数: 0

摘要

很大一部分天体在CCD图像中呈现点形状,如恒星和qso,由于其像素较少,包含的信息较少。单纯基于图像数据的点源分类可能导致精度低。为了解决这一问题,本文提出了一种基于多模态迁移学习的点形天体分类方法。考虑到光谱数据具有丰富的特征,且光谱数据与图像数据之间存在相关性,该方法充分利用天体光谱数据所获得的知识,并将其转移到原始的基于图像的分类中,提高了恒星和qso的分类精度。首先,利用一维残差网络从原始的3700维光谱数据中提取128维光谱特征向量。这个光谱特征向量捕捉了天体的重要特征。然后利用生成对抗网络生成一个128维的模拟光谱向量,该光谱向量对应于天体图像。通过生成模拟光谱矢量,可以获得同一天体的光谱和图像两种模态数据,丰富了模型的输入特征。在即将到来的多模态分类模型中,我们只需要天体图像及其对应的模拟光谱数据,不再需要真实的光谱数据。该方法在光谱数据的辅助下,缓解了原有基于图像的分类方法的上述缺点。值得注意的是,我们的方法将f1得分从0.93提高到0.9777,同时将分类错误率降低了40%。这些改进显著提高了恒星和qso的分类精度,为天体点源的分类提供了有力的支持。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Multimodal Transfer Learning Method for Classifying Images of Celestial Point Sources
Abstract A large fraction of celestial objects exhibit point shapes in CCD images, such as stars and QSOs, which contain less information due to their few pixels. Point source classification based solely on image data may lead to low accuracy. To address this challenge, this paper proposes a Multi-modal Transfer Learning-based classification method for celestial objects with point shape images. Considering that spectral data possess rich features and that there is a correlation between spectral data and image data, the proposed approach fully utilizes the knowledge gained from celestial spectral data and transfers it to the original image-based classification, enhancing the accuracy of classifying stars and QSOs. Initially, a one-dimensional residual network is employed to extract a 128-dimensional spectral feature vector from the original 3700-dimensional spectral data. This spectral feature vector captures important features of the celestial object. The Generative Adversarial Network is then utilized to generate a simulated spectral vector of 128 dimensions, which corresponds to the celestial object image. By generating simulated spectral vectors, data from two modals (spectral and image) for the same celestial object are available, enriching the input features of the model. In the upcoming multimodal classification model, we only require the images of celestial objects along with their corresponding simulated spectral data, and we no longer need real spectral data. With the assistance of spectral data, the proposed method alleviates the above disadvantages of the original image-based classification method. Remarkably, our method has improved the F1-score from 0.93 to 0.9777, while reducing the error rate in classification by 40%. These enhancements significantly increase the classification accuracy of stars and QSOs, providing strong support for the classification of celestial point sources.
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
Publications of the Astronomical Society of the Pacific
Publications of the Astronomical Society of the Pacific 地学天文-天文与天体物理
CiteScore
6.70
自引率
5.70%
发文量
103
审稿时长
4-8 weeks
期刊介绍: The Publications of the Astronomical Society of the Pacific (PASP), the technical journal of the Astronomical Society of the Pacific (ASP), has been published regularly since 1889, and is an integral part of the ASP''s mission to advance the science of astronomy and disseminate astronomical information. The journal provides an outlet for astronomical results of a scientific nature and serves to keep readers in touch with current astronomical research. It contains refereed research and instrumentation articles, invited and contributed reviews, tutorials, and dissertation summaries.
×
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