[1]苗壮,王培龙,崔浩然,等.融合全局上下文关联特征的细粒度图像分类[J].计算机技术与发展,2024,34(06):29-36.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0067]
　MIAO Zhuang,WANG Pei-long,CUI Hao-ran,et al.Fine-grained Image Classification Based on Fusion of Global Contextual Features[J].,2024,34(06):29-36.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0067]
点击复制

融合全局上下文关联特征的细粒度图像分类()

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

卷:
34
期数:
2024年06期
页码:
29-36
栏目:
媒体计算
出版日期:
2024-06-10

文章信息/Info

Title:
Fine-grained Image Classification Based on Fusion of Global Contextual Features
文章编号:
1673-629X(2024)06-0029-08
作者:
苗壮1; 王培龙1; 崔浩然1; 王昱菲2; 王家宝1
1. 陆军工程大学 指挥控制工程学院,江苏 南京 210007;2. 奇安信科技集团股份有限公司 军团 CBG,北京 100044
Author(s):
MIAO Zhuang1; WANG Pei-long1; CUI Hao-ran1; WANG Yu-fei2; WANG Jia-bao1
1. School of Command and Control Engineering,Army Engineering University of PLA,Nanjing 210007,China;2. Legion CBG,Qi’anxin Technology Group Co. ,Ltd. ,Beijing 100044,China
关键词:
细粒度; 图像分类; 注意力; 局部特征; 关联特征
Keywords:
fine grained; image classification; attention; local feature; association feature
分类号:
TP391.41
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0067
摘要:
针对现有基于注意力机制的细粒度图像分类模型在提取图像特征时,过于关注图像目标的某个或某些局部特征,而忽略不同局部特征之间、局部特征和全局特征之间的关联关系的问题,提出了一种融合全局上下文关联特征的细粒度图像分类方法。 该方法设计了区域感知模块,通过从图像中获得不同区域的区域特征感知编码,实现对图像中目标的一个或多个局部区域的特征表示;基于加性注意力机制,设计了全局注意力感知模块和上下文注意力感知模块,通过构建各局部特征之间、局部特征和整体特征之间的关联性,实现对遮挡目标的关键部位特征的更有效表示。 通过在细粒度图像分类数据集 Stanford Cars、FGVC Aircraft、CUB-200-2011 以及自建的 FGVC-LAV 数据集上的验证评估表明,该方法可以在提取图像局部特征的同时,有效挖掘局部特征和局部特征之间、局部特征和全局特征之间的关联关系,提高细粒度图像分类准确率。
Abstract:
A fine-grained image classification method that integrates global contextual features is proposed to address the problem of existing attention mechanism based fine-grained image classification models that overly focus on one or some local features of the image target when extracting image features, while ignoring the correlation between different local features and between local and global features. In this method,a region awareness module is designed to realize the feature representation of one or more local regions of the target in the image by obtaining regional feature perception coding of different regions from the image. Based on the additive attention mechanism, the global attention perception module and the context attention perception module are designed. By constructing the correlation between local features and local features as well as between the local features and the whole features,the key parts of the obscured object can be represented more effectively. Through validation and evaluation on fine-grained image classification datasets such as Stanford Cars,FGVC Aircraft,CUB-200-2011,and the self built FGVC-LAV dataset,it was verified that the proposed method can effectively mine the correlation between local features and local features,as well as between local features and global features,while extracting local features from images,thereby improving the accuracy of fi-ne-grained image classification.

相似文献/References:

[1]张江 王年 梁栋 唐俊.基于Laplace谱的图像分类[J].计算机技术与发展,2008,(05):73.
　ZHANG Jiang,WANG Nian,LIANG Dong,et al.Image Classification Based on Laplacian Spectra[J].,2008,(06):73.
[2]肖威 程文青 许炜.基于Web的工作流细粒度授权框架[J].计算机技术与发展,2006,(12):240.
　XIAO Wei,CHENG Wen-qing,XU Wei.A Web-Based Workflow Authorization Architecture with Fine Granularity[J].,2006,(06):240.
[3]周伟 武港山.基于显著图的花卉图像分类算法研究[J].计算机技术与发展,2011,(11):15.
　ZHOU Wei,WU Gang-shan.Research on Saliency Map Based Flower Image Classification Algorithm[J].,2011,(06):15.
[4]李亚娥,汪西莉.一种自适应的半监督图像分类算法[J].计算机技术与发展,2013,(02):112.
　LI Ya-e,WANG Xi-li.An Adaptive Semi-supervised Image Classification Algorithm[J].,2013,(06):112.
[5]汪旗,贾兆红.基于多示例学习的图像分类算法[J].计算机技术与发展,2014,24(04):88.
　WANG Qi[],JIA Zhao-hong[].Image Categorization by Multi-instance Learning[J].,2014,24(06):88.
[6]郝小龙. 改进的RBAC模型在电网视频监控平台中的应用[J].计算机技术与发展,2014,24(12):212.
　HAO Xiao-long. Application of Improved RBAC Model in Grid Video Monitoring Platform[J].,2014,24(06):212.
[7]武苏雯,赵慧杰,刘 鑫,等.基于迁移学习的图像分类在诗词中的应用研究[J].计算机技术与发展,2021,31(07):215.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 036]
　WU Su-wen,ZHAO Hui-jie,LIU Xin,et al.Research on Application of Image Classification Based onTransfer Learning in Poetry[J].,2021,31(06):215.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 036]
[8]陈彦竹,郝天曙. 基于角色信任度动态监控的访问控制研究[J].计算机技术与发展,2017,27(10):106.
　CHEN Yan-zhu,HAO Tian-shu. Research on Access Control of Dynamic Monitoring with Role Trustrank[J].,2017,27(06):106.
[9]阮航,孙涵.基于 Faster R-CNN 的车辆多属性识别[J].计算机技术与发展,2018,28(10):129.[doi:10.3969/ j. issn.1673-629X.2018.10.027]
　RUAN Hang,SUN Han.Vehicle Multi-attribute Recognition Based on Faster R-CNN[J].,2018,28(06):129.[doi:10.3969/ j. issn.1673-629X.2018.10.027]
[10]王 敏,陈立潮,曹建芳,等.Hadoop 下自适应随机权值多特征融合图像分类[J].计算机技术与发展,2018,28(11):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]
　WANG Min,CHEN Li-chao,CAO Jian-fang,et al.Multi-feature Fusion Image Classification of Adaptive Random Weight Based on Hadoop[J].,2018,28(06):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]

更新日期/Last Update: 2024-06-10