An Image-Retrieval Method Based on Cross-Hardware Platform Features

IF 3.8 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS
Jun Yin, Fei Wu, Hao Su
{"title":"An Image-Retrieval Method Based on Cross-Hardware Platform Features","authors":"Jun Yin, Fei Wu, Hao Su","doi":"10.3390/asi7040064","DOIUrl":null,"url":null,"abstract":"Artificial intelligence (AI) models have already achieved great success in fields such as computer vision and natural language processing. However, deploying AI models based on heterogeneous hardware is difficult to ensure accuracy consistency, especially for precision sensitive feature-based image retrieval. In this article, we realize an image-retrieval method based on cross-hardware platform features, aiming to prove that the features of heterogeneous hardware platforms can be mixed, in which the Huawei Atlas 300V and NVIDIA TeslaT4 are used for experiments. First, we compared the decoding differences of heterogeneous hardware, and used CPU software decoding to help hardware decoding improve the decoding success rate. Then, we compared the difference between the Atlas 300V and TeslaT4 chip architectures and tested the differences between the two platform features by calculating feature similarity. In addition, the scaling mode in the pre-processing process was also compared to further analyze the factors affecting feature consistency. Next, the consistency of capture and correlation based on video structure were verified. Finally, the experimental results reveal that the feature results from the TeslaT4 and Atlas 300V can be mixed for image retrieval based on cross-hardware platform features. Consequently, cross-platform image retrieval with low error is realized. Specifically, compared with the Atlas 300V hard and CPU soft decoding, the TeslaT4 hard decoded more than 99% of the image with a decoding pixel maximum difference of +1/−1. From the average of feature similarity, the feature similarity between the Atlas 300V and TeslaT4 exceeds 99%. The difference between the TeslaT4 and Atlas 300V in recall and mAP in feature retrieval is less than 0.1%.","PeriodicalId":36273,"journal":{"name":"Applied System Innovation","volume":null,"pages":null},"PeriodicalIF":3.8000,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied System Innovation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/asi7040064","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

Artificial intelligence (AI) models have already achieved great success in fields such as computer vision and natural language processing. However, deploying AI models based on heterogeneous hardware is difficult to ensure accuracy consistency, especially for precision sensitive feature-based image retrieval. In this article, we realize an image-retrieval method based on cross-hardware platform features, aiming to prove that the features of heterogeneous hardware platforms can be mixed, in which the Huawei Atlas 300V and NVIDIA TeslaT4 are used for experiments. First, we compared the decoding differences of heterogeneous hardware, and used CPU software decoding to help hardware decoding improve the decoding success rate. Then, we compared the difference between the Atlas 300V and TeslaT4 chip architectures and tested the differences between the two platform features by calculating feature similarity. In addition, the scaling mode in the pre-processing process was also compared to further analyze the factors affecting feature consistency. Next, the consistency of capture and correlation based on video structure were verified. Finally, the experimental results reveal that the feature results from the TeslaT4 and Atlas 300V can be mixed for image retrieval based on cross-hardware platform features. Consequently, cross-platform image retrieval with low error is realized. Specifically, compared with the Atlas 300V hard and CPU soft decoding, the TeslaT4 hard decoded more than 99% of the image with a decoding pixel maximum difference of +1/−1. From the average of feature similarity, the feature similarity between the Atlas 300V and TeslaT4 exceeds 99%. The difference between the TeslaT4 and Atlas 300V in recall and mAP in feature retrieval is less than 0.1%.
基于跨硬件平台特征的图像检索方法
人工智能(AI)模型已经在计算机视觉和自然语言处理等领域取得了巨大成功。然而,在异构硬件上部署人工智能模型很难确保准确性的一致性,尤其是对精度敏感的基于特征的图像检索。本文以华为 Atlas 300V 和英伟达 TeslaT4 为实验对象,实现了一种基于跨硬件平台特征的图像检索方法,旨在证明异构硬件平台的特征可以混合使用。首先,我们比较了异构硬件的解码差异,利用 CPU 软件解码帮助硬件解码提高解码成功率。然后,我们比较了 Atlas 300V 和 TeslaT4 芯片架构之间的差异,并通过计算特征相似度测试了两个平台特征之间的差异。此外,还比较了预处理过程中的缩放模式,进一步分析了影响特征一致性的因素。接着,验证了基于视频结构的捕捉一致性和相关性。最后,实验结果表明,TeslaT4 和 Atlas 300V 的特征结果可以混合用于基于跨硬件平台特征的图像检索。因此,实现了低误差的跨平台图像检索。具体来说,与 Atlas 300V 硬解码和 CPU 软解码相比,TeslaT4 硬解码的图像超过 99%,解码像素最大差值为 +1/-1 。从特征相似度的平均值来看,Atlas 300V 和 TeslaT4 的特征相似度超过 99%。在特征检索的召回率和 mAP 方面,TeslaT4 与 Atlas 300V 的差异小于 0.1%。
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 求助全文
来源期刊
Applied System Innovation
Applied System Innovation Mathematics-Applied Mathematics
CiteScore
7.90
自引率
5.30%
发文量
102
审稿时长
11 weeks
×
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