[1]林益文,杨 啸,陈 青,等.基于距离损失函数的特征融合模型[J].计算机技术与发展,2023,33(12):72-78.[doi:10. 3969 / j. issn. 1673-629X. 2023. 12. 010]
　LIN Yi-wen,YANG Xiao,CHEN Qing,et al.Feature Fusion Model Based on Distance Loss Function[J].,2023,33(12):72-78.[doi:10. 3969 / j. issn. 1673-629X. 2023. 12. 010]
点击复制

基于距离损失函数的特征融合模型()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年12期
页码:
72-78
栏目:
媒体计算
出版日期:
2023-12-10

文章信息/Info

Title:
Feature Fusion Model Based on Distance Loss Function
文章编号:
1673-629X(2023)12-0072-07
作者:
林益文; 杨 啸; 陈 青; 邱新媛; 任维泽
中国核动力研究设计院,四川 成都 610213
Author(s):
LIN Yi-wen; YANG Xiao; CHEN Qing; QIU Xin-yuan; REN Wei-ze
Nuclear Power Institute of China,Chengdu 610213,China
关键词:
深度学习; 卷积神经网络; 语义特征; 距离函数; 模型融合
Keywords:
deep learning; convolutional neural network; semantic feature; distance function; model fusion
分类号:
TP183
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 12. 010
摘要:
卷积神经网络在图像识别任务中表现出出色的学习语义特征的能力,实现了相关目标对象的高精度检测,然而其通常只关注图像最具识别能力的特定区域,忽视了部分有价值的语义特征。 为提高卷积神经网络的识别能力,提出一种基于距离损失函数的特征融合模型。 该方法利用欧氏余弦复合距离损失函数迫使基础模型学习具有差异的特征概念,通过并置特征融合法整合差异化的特征概念进行目标识别。 实验使用了多种基准卷积神经网络骨架、数个流行数据集和不同样本量进行多因素交叉分析,从准确率数据和类激活图两个方面证实了该方法能够丰富基础模型语义特征的多样性,提升融合模型的识别性能,并且具有有效性和普遍性,同时利用数学统计方法也揭示了该方法的应用特征与优势。
Abstract:
Convolutional neural networks have shown excellent ability to learn semantic features in image recognition tasks and realizedhighly accurate detection of relevant target object. However, it usually only focuses on specific regions of the image with the mostrecognition power,ignoring some valuable semantic features. To improve the recognition capability of convolutional neural networks,wepropose a feature fusion model based on distance loss function. The Euclidean -Cosine distance loss function is used to force the basemodels to learn differentiated feature concepts, and the concatenation feature fusion method is implemented to integrate differentiatedfeature concepts for the image recognition. Experiments are conducted using different benchmark convolutional neural networks,severalpopular datasets and different sample sizes for multi-factor cross-tabulation analysis. It爷 s confirmed that the proposed method can enrichthe diversity of semantic features of the base models,and improve the recognition performance of the fusion model in terms of accuracyvalues and class activation maps. The validity and generality of the proposed method can also be guaranteed in this way. Meanwhile,theapplication characteristics and advantages of the method are also revealed using mathematical statistical methods.

相似文献/References:

[1]张丹丹,李雷. 基于PCANet-RF的人脸检测系统[J].计算机技术与发展,2016,26(02):31.
　ZHANG Dan-dan,LI Lei. Face Detection System Based on PCANet-RF[J].,2016,26(12):31.
[2]邓宗平,赵启军,陈虎. 基于深度学习的人脸姿态分类方法[J].计算机技术与发展,2016,26(07):11.
　DEND Zong-ping,ZHAO Qi-jun,CHEN Hu. Face Pose Classification Method Based on Deep Learning[J].,2016,26(12):11.
[3]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(12):19.
[4]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(12):1.
[5]戴晓薇,赵启军. 基于回归的指纹方向场估计[J].计算机技术与发展,2017,27(01):1.
　DAI Xiao-wei,ZHAO Qi-jun. Fingerprint Orientation Field Estimation Based on Regression[J].,2017,27(12):1.
[6]曾志平[] [],萧海东[],张新鹏[]. 基于DBN的金融时序数据建模与决策[J].计算机技术与发展,2017,27(04):1.
　ZENG Zhi-ping[] [],XIAO Hai-dong[],ZHANG Xin-peng[]. Modeling and Decision-making of Financial Time Series Data with DBN[J].,2017,27(12):1.
[7]周成伟. 基于卷积神经网络的自然场景中数字识别[J].计算机技术与发展,2017,27(11):101.
　ZHOU Cheng-wei. Recognition of Numbers in Natural Scene with Convolutional Neural Network[J].,2017,27(12):101.
[8]傅 鹏,谢世朋.基于级联卷积神经网络的车牌定位[J].计算机技术与发展,2018,28(01):134.[doi:10.3969/ j. issn.1673-629X.2018.01.029]
　FU Peng,XIE Shi-peng.License Plate Location Based on Cascaded Convolution Neural Network[J].,2018,28(12):134.[doi:10.3969/ j. issn.1673-629X.2018.01.029]
[9]崔凤焦.表情识别算法研究进展与性能比较[J].计算机技术与发展,2018,28(02):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
　CUI Feng-jiao.Ｒesearch and Performance Comparison of Facial Expression Ｒecognition Algorithm[J].,2018,28(12):145.[doi:10．3969/j．issn．1673－629X．2018．02．031]
[10]吴 超,邵 曦.基于深度学习的指静脉识别研究[J].计算机技术与发展,2018,28(02):200.[doi:10．3969/j．issn．1673－629X．2018．02．043]
　WU Chao,SHAO Xi.Research on Finger Vein Ｒecognition Based on Deep Learning[J].,2018,28(12):200.[doi:10．3969/j．issn．1673－629X．2018．02．043]
[11]李宏林. 分析式纹理合成技术及其在深度学习的应用[J].计算机技术与发展,2017,27(11):7.
　LI Hong-lin. Analyzed Texture-synthesis Techniques and Their Applications in Deep Learning[J].,2017,27(12):7.
[12]曲之琳,胡晓飞.基于改进激活函数的卷积神经网络研究[J].计算机技术与发展,2017,27(12):77.[doi:10.3969/ j. issn.1673-629X.2017.12.017]
　QU Zhi-lin,HU Xiao-fei.Research on Convolutional Neural Network Based on Improved Activation Function[J].,2017,27(12):77.[doi:10.3969/ j. issn.1673-629X.2017.12.017]
[13]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(12):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[14]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(12):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[15]阮航,王立春.基于特征图的车辆检测和分类[J].计算机技术与发展,2018,28(11):39.[doi:10.3969/ j. issn.1673-629X.2018.11.009]
　RUAN Hang,WANG Li-chun.Vehicle Detection and Classification Based on Feature Map[J].,2018,28(12):39.[doi:10.3969/ j. issn.1673-629X.2018.11.009]
[16]刘华春.卷积神经网络在车牌识别中的应用研究[J].计算机技术与发展,2019,29(04):128.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 026]
　LIU Hua-chun.Research on Application of Convolutional Neural Network in License Plate Recognition[J].,2019,29(12):128.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 026]
[17]倪申龙,曾接贤,周世健.整体车牌图像超分辨率重建研究[J].计算机技术与发展,2019,29(04):195.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 039]
　NI Shen-long,ZENG Jie-xian,ZHOU Shi-jian.Study on Reconstruction of Overall Image of License Plate[J].,2019,29(12):195.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 039]
[18]王山海,刘谦,马鑫鑫.基于图像识别的人工影响天气业务的研究[J].计算机技术与发展,2019,29(05):172.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 036]
　WANG Shan-hai,LIU Qian,MA Xin-xin.Research on Weather Modification Based on Image Recognition[J].,2019,29(12):172.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 036]
[19]刘华春,侯向宁.采用视觉显著性和卷积网络的车牌定位算法[J].计算机技术与发展,2019,29(06):74.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 016]
　LIU Hua-chun,HOU Xiang-ning.A License Plate Location Algorithm Using Visual Saliency and Convolutional Network[J].,2019,29(12):74.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 016]
[20]黄 鹤,荆晓远,董西伟,等.基于 Skip-gram 的 CNNs 文本邮件分类模型[J].计算机技术与发展,2019,29(06):143.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 030]
　HUANG He,JING Xiao-yuan,DONG Xi-wei,et al.CNNs-Highway Text Message Classification Model Based on Skip-gram[J].,2019,29(12):143.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 030]

更新日期/Last Update: 2023-12-10