POSS-CNN: An Automatically Generated Convolutional Neural Network with Precision and Operation Separable Structure Aiming at Target Recognition and Detection

IF 2.4 Q3 COMPUTER SCIENCE, INFORMATION SYSTEMS Information (Switzerland) Pub Date : 2023-11-07 DOI:10.3390/info14110604
Jia Hou, Jingyu Zhang, Qi Chen, Siwei Xiang, Yishuo Meng, Jianfei Wang, Cimang Lu, Chen Yang
{"title":"POSS-CNN: An Automatically Generated Convolutional Neural Network with Precision and Operation Separable Structure Aiming at Target Recognition and Detection","authors":"Jia Hou, Jingyu Zhang, Qi Chen, Siwei Xiang, Yishuo Meng, Jianfei Wang, Cimang Lu, Chen Yang","doi":"10.3390/info14110604","DOIUrl":null,"url":null,"abstract":"Artificial intelligence is changing and influencing our world. As one of the main algorithms in the field of artificial intelligence, convolutional neural networks (CNNs) have developed rapidly in recent years. Especially after the emergence of NASNet, CNNs have gradually pushed the idea of AutoML to the public’s attention, and large numbers of new structures designed by automatic searches are appearing. These networks are usually based on reinforcement learning and evolutionary learning algorithms. However, sometimes, the blocks of these networks are complex, and there is no small model for simpler tasks. Therefore, this paper proposes POSS-CNN aiming at target recognition and detection, which employs a multi-branch CNN structure with PSNC and a method of automatic parallel selection for super parameters based on a multi-branch CNN structure. Moreover, POSS-CNN can be broken up. By choosing a single branch or the combination of two branches as the “benchmark”, as well as the overall POSS-CNN, we can achieve seven models with different precision and operations. The test accuracy of POSS-CNN for a recognition task tested on a CIFAR10 dataset can reach 86.4%, which is equivalent to AlexNet and VggNet, but the operation and parameters of the whole model in this paper are 45.9% and 45.8% of AlexNet, and 29.5% and 29.4% of VggNet. The mAP of POSS-CNN for a detection task tested on the LSVH dataset is 45.8, inferior to the 62.3 of YOLOv3. However, compared with YOLOv3, the operation and parameters of the model in this paper are reduced by 57.4% and 15.6%, respectively. After being accelerated by WRA, POSS-CNN for a detection task tested on an LSVH dataset can achieve 27 fps, and the energy efficiency is 0.42 J/f, which is 5 times and 96.6 times better than GPU 2080Ti in performance and energy efficiency, respectively.","PeriodicalId":38479,"journal":{"name":"Information (Switzerland)","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information (Switzerland)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/info14110604","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

Artificial intelligence is changing and influencing our world. As one of the main algorithms in the field of artificial intelligence, convolutional neural networks (CNNs) have developed rapidly in recent years. Especially after the emergence of NASNet, CNNs have gradually pushed the idea of AutoML to the public’s attention, and large numbers of new structures designed by automatic searches are appearing. These networks are usually based on reinforcement learning and evolutionary learning algorithms. However, sometimes, the blocks of these networks are complex, and there is no small model for simpler tasks. Therefore, this paper proposes POSS-CNN aiming at target recognition and detection, which employs a multi-branch CNN structure with PSNC and a method of automatic parallel selection for super parameters based on a multi-branch CNN structure. Moreover, POSS-CNN can be broken up. By choosing a single branch or the combination of two branches as the “benchmark”, as well as the overall POSS-CNN, we can achieve seven models with different precision and operations. The test accuracy of POSS-CNN for a recognition task tested on a CIFAR10 dataset can reach 86.4%, which is equivalent to AlexNet and VggNet, but the operation and parameters of the whole model in this paper are 45.9% and 45.8% of AlexNet, and 29.5% and 29.4% of VggNet. The mAP of POSS-CNN for a detection task tested on the LSVH dataset is 45.8, inferior to the 62.3 of YOLOv3. However, compared with YOLOv3, the operation and parameters of the model in this paper are reduced by 57.4% and 15.6%, respectively. After being accelerated by WRA, POSS-CNN for a detection task tested on an LSVH dataset can achieve 27 fps, and the energy efficiency is 0.42 J/f, which is 5 times and 96.6 times better than GPU 2080Ti in performance and energy efficiency, respectively.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
POSS-CNN:一种针对目标识别和检测的具有精度和操作可分结构的自动生成卷积神经网络
人工智能正在改变和影响我们的世界。卷积神经网络(convolutional neural networks, cnn)作为人工智能领域的主要算法之一,近年来发展迅速。特别是在NASNet出现之后,cnn逐渐将AutoML的思想推向了大众的视野,大量由自动搜索设计的新结构正在出现。这些网络通常基于强化学习和进化学习算法。然而,有时候,这些网络的块是复杂的,对于更简单的任务没有小的模型。因此,本文提出了针对目标识别和检测的POSS-CNN,该方法采用了一种带有PSNC的多分支CNN结构和一种基于多分支CNN结构的超参数自动并行选择方法。此外,POSS-CNN可以被分解。通过选择单个分支或两个分支的组合作为“基准”,以及整体POSS-CNN,我们可以得到7个精度和操作不同的模型。POSS-CNN在CIFAR10数据集上测试的一个识别任务的测试准确率可以达到86.4%,与AlexNet和VggNet相当,但本文整个模型的运算和参数分别为AlexNet的45.9%和45.8%,VggNet的29.5%和29.4%。POSS-CNN在LSVH数据集上测试的检测任务mAP为45.8,低于YOLOv3的62.3。但与YOLOv3相比,本文模型的运算和参数分别减少了57.4%和15.6%。经过WRA加速后,在LSVH数据集上测试的POSS-CNN检测任务可以达到27 fps,能量效率为0.42 J/f,性能和能量效率分别是GPU 2080Ti的5倍和96.6倍。
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 去求助
来源期刊
Information (Switzerland)
Information (Switzerland) Computer Science-Information Systems
CiteScore
6.90
自引率
0.00%
发文量
515
审稿时长
11 weeks
期刊最新文献
Weakly Supervised Learning Approach for Implicit Aspect Extraction Science Mapping of Meta-Analysis in Agricultural Science An Integrated Time Series Prediction Model Based on Empirical Mode Decomposition and Two Attention Mechanisms Context-Aware Personalization: A Systems Engineering Framework Polarizing Topics on Twitter in the 2022 United States Elections
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1