06 基于分组卷积的无监督注意机制行人重识别方法研究

杨东贺,任国印,张晓琳

• 1:内蒙古科技大学信息工程学院

• 
  

摘要(Abstract)：

针对传统的行人重识别算法需要依赖大量带标签的行人图像数据，以及系统难以部署等问题，提出使用ResNet50作为模型的骨干网络.通过增加CBAM注意力机制，分组卷积，层次聚类和实例学习等方法实现无监督行人重识别.同时，使用欧式距离来进行相似性度量，对最终识别结果加以验证.实验结果表明：所提出的基于分组卷积的无监督注意机制行人重识别方法能够提高网络模型在未知数据域的泛化能力，减少了模型的训练参数.

关键词(KeyWords)： 行人重识别;无监督;注意力机制;分组卷积

基金项目(Foundation): 国家自然科学基金资助项目(61771266);; 内蒙古自治区高等学校科学研究资助项目(NJZY23081)

作者(Author): 杨东贺,任国印,张晓琳

DOI: 10.16559/j.cnki.2095-2295.2023.02.006

参考文献(References)：

• [1] XIONG F,XIAO Y,CAO Z,et al.Good practices on building effective CNN baseline model for person re identification[C]//Proceedings of the international conference on graphics and image processing.Bellingham,USA:SPIE,2018:142.

• [2] ZHANG C,WU Y,LEI T.Unsupervised region attention network for person re-Identification[J].IEEE Access,2019,7:165520.

• [3] DENG W,ZHENG L,YE Q,et al.Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.Piscataway,USA:IEEE Computer Society,2018:994.

• [4] WANG D,ZHANG S.Unsupervised person re-identification via multi-label classification[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.piscataway,USA:IEEE Computer Society,2020:10978.

• [5] LIN Y,DONG X,ZHENG L,et al.A bottom-up clustering approach to unsupervised person re-identification[C]//Proceedings of the AAAI conference on artificial intelligence.Menlo Park,USA:AAAI,2019:8738.

• [6] WOO S,PARK J,LEE J Y,et al.Cbam:Convolutional block attention module[C]//Proceedings of the european conference on computer vision.Berlin,German:Springer,2018:3.

• [7] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.piscataway,USA:IEEE Computer Society,2016:770.

• [8] IOANNOU Y,ROBERTSON D,CIPOLLA R,et al.Deep roots:Improving cnn efficiency with hierarchical filter groups[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.Piscataway,USA:IEEE,2017:5977.

• [9] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(06):84.

• [10] HINTON G,VINYALS O,DEAN J.Distilling the knowledge in a neural network[J].arXiv preprint arXiv,2015,2(07):1503.02531.

• [11] ZHENG L,SHEN L,TIAN L,et al.Scalable person re-identification:A benchmark[C]//Proceedings of the IEEE international conference on computer vision.Piscataway,USA:IEEE,2015:1116.

• [12] FAN H,ZHENG L,YAN C,et al.Unsupervised person re-identification:Clustering and fine-tuning[J].ACM Transactions on Multimedia Computing,Communicati- ons,and Applications,2018,14(04):1.

• [13] LV J,CHEN W,LI Q,et al.Unsupervised cross-dataset person re-identification by transfer learning of spatial-temporal patterns[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.Piscataway,USA:IEEE Computer Society,2018:7948.

• [14] WU Y,LIN Y,DONG X,et al.Exploit the unknown gradually:One-shot video-based person re-identification by stepwise learning[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.Piscataway,USA:IEEE Computer Society,2018:5177.

• [15] ZOU Y,YANG X,YU Z,et al.Joint disentangling and adaptation for cross-domain person re-identification[C]// Proceedings of the European conference on computer vision.Berlin,German:Springer,2020:87.

• [16] YANG R,WU S,XIAO G.Unsupervised multiple granularities attention-Attribute learning for person re-Identification[C]//Proceedings of the IEEE international symposium on circuits and systems.Piscataway,USA:IEEE,2020:1.

• [17] ZHENG K,LIU W,HE L,et al.Group-aware label transfer for domain adaptive person re-identification [C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.Piscataway,USA:IEEE Computer Society,2021:5306.