递归深度混合关注网络的细粒度图像分类方法

doi:10.19678/j.issn.1000-3428.0051191

计算机工程 ›› 2019, Vol. 45 ›› Issue (5): 205-209. doi: 10.19678/j.issn.1000-3428.0051191

递归深度混合关注网络的细粒度图像分类方法

桂江生¹,麻陈飞¹,包晓安¹,钱俊彦²

1.浙江理工大学信息学院,杭州 310018; 2.桂林电子科技大学广西可信软件重点实验室,广西桂林 541004

收稿日期:2018-04-12 出版日期:2019-05-15 发布日期:2019-05-15
作者简介:桂江生(1978—),男,副教授,主研方向为计算机视觉、模式识别;麻陈飞,硕士研究生;包晓安、钱俊彦,教授。
基金资助:
国家自然科学基金(61502430,61562015);浙江省重大科技专项重点工业项目(2014C01047);广西自然科学重点基金(2015GXNSFDA139038)。

Fine-grained Image Classification Method for Recurrent Deep Hybrid Attention Network

GUI Jiangsheng¹,MA Chenfei¹,BAO Xiaoan¹,QIAN Junyan²

1.School of Informatics Science and Technology,Zhejiang Sci-tech University,Hangzhou 310018,China; 2.Guangxi Key Laboratory of Trusted Software,Guilin University of Electronic Technology,Guilin,Guangxi 541004,China

Received:2018-04-12 Online:2019-05-15 Published:2019-05-15

摘要/Abstract

摘要：

在细粒度图像的大量局部特征中,只有少量特征具有判别性,其提取较为困难。为此,提出递归深度混合关注网络方法。通过在卷积结构单元中添加通道关注模块和空间关注模块,实现网络的混合关注。以第1路网络输出特征的空间响应值为依据切割原图,并将切割后的图像放大输入第2路网络,进行由粗到细的网络递归。将2路网络提取的特征进行级联融合。在公开数据集Stanford Dogs、Stanford Cars中进行对比实验,结果表明,该方法的分类精度分别为87.1%、92.4%,优于FCAN、HIHCA等方法。

关键词: 细粒度图像分类, 卷积神经网络, 通道关注, 空间关注, 递归网络

Abstract:

Among the large number of local features of fine-grained images,only a few of them are discriminative and are very difficult to extract.To solve this problem,a recurrent deep hybrid attention network is proposed.By adding channel attention module and spatial attention module into convolution units,the hybrid attention network is realized.Based on the spatial response value of the output feature of the first network,the original image is segmented,and the segmented image is enlarged and input into the second network to realize the coarse-to-fine network recursion.The features extracted from two networks are cascaded to achieve the purpose of feature fusion.Experiments are conducted in the open data sets.Stanford Dogs and Stanford Cars.Results show that the classification accuracies of the proposed algorithm are 87.1% and 92.4%,respectively,which is better than FCAN,HIHCA and other methods.

Key words: fine-grained image classification, convolutional neural network, channel attention, spatial attention, recurrent network

中图分类号:

TP391

桂江生,麻陈飞,包晓安,钱俊彦. 递归深度混合关注网络的细粒度图像分类方法[J]. 计算机工程, 2019, 45(5): 205-209.

GUI Jiangsheng,MA Chenfei,BAO Xiaoan,QIAN Junyan. Fine-grained Image Classification Method for Recurrent Deep Hybrid Attention Network[J]. Computer Engineering, 2019, 45(5): 205-209.

http://www.ecice06.com/CN/Y2019/V45/I5/205

参考文献

［1］SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition［J］.Computer Science,2014:1.
［2］HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Deep residual learning for image recognition［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:770-778.
［3］HUANG Gao,LIU Zhuang,MAATEN L V D,et al.Densely connected convolutional networks［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:4700-4708.
［4］李炳政.关于智能交通中的车型识别分析［J］.数字技术与应用,2016(4):230-230.
［5］冯琼瑛,陈粤超,张家善,等.红树林湿地鸟类查询与鉴别系统的设计与实现［J］.计算机应用与软件,2016,33(9):64-66.
［6］KIAPOUR M H,HAN Xufeng,LAZEBNIK S,et al.Where to buy it:matching street clothing photos in online shops［C］//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2015:3343-3351.
［7］陈玄,朱荣,王中元.基于融合卷积神经网络模型的手写数字识别［J］.计算机工程,2017,43(11):187-192.
［8］易生,梁华刚,茹锋.基于多列深度3D卷积神经网络的手势识别［J］.计算机工程,2017,43(8):243-248.
［9］GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:580-587.
［10］KRAUSE J,JIN Hailin.Fine-grained recognition without part annotations［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:5546-5555.
［11］LAM M,MAHASSENI B.Fine-grained recognition as HSnet search for informative image parts［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:6497-6506.
［12］ROYCHOWDHURY A.Bilinear CNN models for fine-grained visual recognition［C］//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2015:1449-1457.
［13］KRAUSE J,STARK M,JIA Deng,et al.3D object representations for fine-grained categorization［C］//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2014:554-561.
［14］KHOSLA A,JAYADEVAPRAKASH N,YAO Bangpeng,et al.Novel dataset for fine-grained image categorization［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2011.
［15］LIU Xiao,XIA Tian,WANG Jiang,et al.Fully convolutional attention localization networks:efficient attention localization for fine-grained recognition［EB/OL］.［2018-03-12］.https://arxiv.org/pdf/1603.06765.pdf.
［16］ZHAO Bo,WU Xiao,FENG Jiashi,et al.Diversified visual attention networks for fine-grained object classifica-tion［J］.IEEE Transactions on Multimedia,2017,19(6):1245-1256.
［17］FU Jianlong,ZHENG Heliang,MEI Tao.Look closer to see better:recurrent attention convolutional neural network for fine-grained image recognition［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:4438-4446.
［18］KONG Shu,FOWLKES C.Low-rank bilinear pooling for fine-grained classification［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:365-374.
［19］CAI Sijia,ZUO Wangmeng,ZHANG Lei.Higher-order integration of hierarchical convolutional activations for fine-grained visual categorization［C］//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2017:511-520.

[1]	曹坪, 杨怀志, 薄一军, 尤嘉, 张淳杰, 李丹勇. 面向低质量裂缝图像的多知识蒸馏分类[J]. 计算机工程, 2023, 49(7): 204-213.
[2]	白明昌. 基于折叠路径聚合的属性网络节点嵌入方法[J]. 计算机工程, 2023, 49(7): 76-84.
[3]	代祖华, 刘园园, 狄世龙. 语义增强的图神经网络方面级文本情感分析[J]. 计算机工程, 2023, 49(6): 71-80.
[4]	沈学利, 田桂源, 姜彦吉, 马琳琳. 基于双阶段Conv-Transformer的时频域语音增强算法[J]. 计算机工程, 2023, 49(6): 123-130.
[5]	丁子轩, 俞雷, 张娟, 李想, 王新宇. 基于深度残差自适应注意力网络的图像超分辨率重建[J]. 计算机工程, 2023, 49(5): 231-238.
[6]	石进, 徐杨, 曹斌. 基于自适应三线性池化网络的细粒度图像分类[J]. 计算机工程, 2023, 49(5): 239-246,254.
[7]	陈治旭, 靳雁霞, 芦烨, 杨晶, 刘亚变, 史志儒. 基于子图卷积神经网络的多精度服装建模方法[J]. 计算机工程, 2023, 49(4): 174-181.
[8]	徐康, 李霏, 姬东鸿. 结合依存图卷积与文本片段搜索的方面情感三元组抽取[J]. 计算机工程, 2023, 49(4): 61-67.
[9]	衡红军, 苗菁. 语义与句法信息加强的二元标记实体关系联合抽取[J]. 计算机工程, 2023, 49(4): 77-84.
[10]	钟宝荣, 吴夏灵. 基于高分辨率网络的轻量型人体姿态估计研究[J]. 计算机工程, 2023, 49(4): 226-232,239.
[11]	杨晶晶, 谢海燕, 薛妮妮, 张傲明. 基于双通道残差网络的水下图像去噪研究[J]. 计算机工程, 2023, 49(4): 188-198.
[12]	刘晶晶, 黄浩. 引入非局部模块卷积神经网络的基频提取模型[J]. 计算机工程, 2023, 49(3): 128-133,160.
[13]	邹长龙, 安敬民, 李冠宇. 基于邻域聚合与CNN的知识图谱实体类型补全[J]. 计算机工程, 2023, 49(3): 134-141.
[14]	翟社平, 张宇航, 柏晓夏. 融合实体邻域信息的知识图谱嵌入负采样方法[J]. 计算机工程, 2023, 49(3): 95-104.
[15]	程小辉, 李钰, 康燕萍. 基于中间图特征提取的卷积网络双标准剪枝[J]. 计算机工程, 2023, 49(3): 105-112.

选择文件类型/文献管理软件名称

选择包含的内容

递归深度混合关注网络的细粒度图像分类方法

Fine-grained Image Classification Method for Recurrent Deep Hybrid Attention Network

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

递归深度混合关注网络的细粒度图像分类方法

Fine-grained Image Classification Method for Recurrent Deep Hybrid Attention Network

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价