[1]沈宇麒,崔衍.基于双层路由注意力及特征融合的细粒度图像分类[J].计算机技术与发展,2024,34(06):23-28.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0072]
　SHEN Yu-qi,CUI Yan.Fine-grained Image Classification Based on Bi-level RoutingAttention and Feature Fusion[J].,2024,34(06):23-28.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0072]
点击复制

基于双层路由注意力及特征融合的细粒度图像分类()

《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:
23-28
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 Bi-level RoutingAttention and Feature Fusion
文章编号:
1673-629X(2024)06-0023-06
作者:
沈宇麒; 崔衍
南京邮电大学 物联网学院,江苏 南京 210003
Author(s):
SHEN Yu-qi; CUI Yan
School of Internet of Things,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
关键词:
细粒度图像分类; 神经网络; 视觉Transformer; 注意力机制; 特征融合
Keywords:
fine-grained image classification; neural network; vision Transformer; attention mechanism; feature fusion
分类号:
TP391.41
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0072
摘要:
近年来,视觉 Transformer(Vision Transformer,ViT)在图像识别领域取得了突破性进展,其自注意力机制能够从图像中提取出不同像素块的判别性标记信息,进而提升图像分类的精度。 在图像分类领域中,细粒度图像分类具有类与类之间的特征差距小、类内的特征差距大的特点,从而导致了分类困难。 针对细粒度图像分类中数据分布具有小型、非均匀和难以发现类与类之间的差异等特征,提出一种基于双层路由注意力(Bi-level Routing Attention,BRA)的细粒度图像分类模型。 基准骨干网络采用多阶段层级架构设计的新型视觉 Transformer 模型作为视觉特征提取器,从中获得局部信息和全局信息以及多尺度的特征。 同时引入特征增强、融合模块,以此提高网络对关键特征的学习能力。 实验结果表明,该模型在 CUB-200-2011 和 Stanford Dogs 这两个细粒度图像数据集上的分类精度分别达到了 91. 7% 和 92. 2% ,相较于多个主流细粒度图像分类模型,该模型具有更好的分类结果。
Abstract:
In recent years,Vision Transformer (ViT) has made a breakthrough in the field of image recognition. Its self-attention module can extract discriminative labeling information of different pixel blocks from images, thereby improving the accuracy of image classification. In the field of image classification,fine-grained image classification is difficult to classify due to the characteristics of small feature differences between classes and large feature differences within classes. A fine-grained image classification model based on Bi-level Routing Attention (BRA) is proposed to address the characteristics of small,non-uniform,and imperceptible differences between classes in data distribution in fine-grained image classification. The benchmark backbone network adopts a new visual Transformer model designed with a multi-stage hierarchical architecture as the visual feature extractor,which obtains local and global information as well as multi-scale features. At the same time,feature boosting and fusion modules are introduced to improve the network’s learning ability for key features. The experimental results show that the classification accuracy of such model on two fine-grained image datasets,CUB-200-2011 and Stanford Dogs,reaches 91. 7% and 92. 2% . Compared with multiple mainstream fine-grained image classification models,such model has better classification results.

相似文献/References:

[1]路川 胡欣杰.区域航空市场航线客流量预测研究[J].计算机技术与发展,2010,(04):84.
　LU Chuan,HU Xin-jie.Analysis of Regional Airline Passenger Forecast Title[J].,2010,(06):84.
[2]高峥 陈蜀宇 李国勇.混合入侵检测系统的研究[J].计算机技术与发展,2010,(06):148.
　GAO Zheng,CHEN Shu-yu,LI Guo-yong.Research of a Hybrid Intrusion Detection System[J].,2010,(06):148.
[3]李志俊 程家兴 金奎 饶玉佳.基于样本期望训练数的BP神经网络改进研究[J].计算机技术与发展,2009,(05):103.
　LI Zhi-jun,CHENG Jia-xing,JIN Kui,et al.BP Algorithm Improvement Based on Sample Expected Training Number[J].,2009,(06):103.
[4]李龙澍 葛瑞峰 王慧萍.基于神经网络的批强化学习在Robocup中的应用[J].计算机技术与发展,2009,(07):98.
　LI Long-shu,GE Rui-feng,WANG Hui-ping.Application of Batch Reinforcement Learning Based on NN to Robocup[J].,2009,(06):98.
[5]贾志先.神经网络在空白试卷识别中的应用[J].计算机技术与发展,2009,(08):208.
　JIA Zhi-xian.Application of Neural Network in Recognization Blank Examination Paper[J].,2009,(06):208.
[6]肖宜龙 路游 亓永刚.基于神经网络的NURBS曲面重建[J].计算机技术与发展,2009,(09):65.
　XIAO Yi-long,LU You,QI Yong-gang.NURBS Surface Reconstruction Based on Neural Network[J].,2009,(06):65.
[7]蔡秋茹 罗烨 柳益君 叶飞跃.企业资信的BP神经网络评估模型研究[J].计算机技术与发展,2009,(10):117.
　CAI Qiu-ru,LUO Ye,LIU Yi-jun,et al.Research on BP Neural Network Model for Corporation Credit Rating[J].,2009,(06):117.
[8]王晓敏 刘希玉 戴芬.BP神经网络预测算法的改进及应用[J].计算机技术与发展,2009,(11):64.
　WANG Xiao-min,LIU Xi-yu,DAI Fen.Improvement and Application of BP Neural Network Forecasting Algorithm[J].,2009,(06):64.
[9]崔海青 刘希玉.基于粒子群算法的RBF网络参数优化算法[J].计算机技术与发展,2009,(12):117.
　CUI Hai-qing,LIU Xi-yu.Parameter Optimization Algorithm of RBF Neural Network Based on PSO Algorithm[J].,2009,(06):117.
[10]张莉 姜浩 蒲安建.基于广义径向基函数的神经网络分类预测[J].计算机技术与发展,2009,(03):106.
　ZHANG Li,JIANG Hao,PU An-jian.Classification and Prediction of Neural Network Based on Generalized Radial Basis Function[J].,2009,(06):106.

更新日期/Last Update: 2024-06-10