贺南南,张荣国,王晓,李建伟,胡静

• 1:太原科技大学计算机科学与技术学院

摘要(Abstract)：

针对行人重识别中行人姿态变化和遮挡问题，提出了一种结合注意机制和局部擦除的行人重识别方法。首先，构建由ResNet50为全局分支和注意擦除为局部分支组成的双分支网络。全局分支用来提取全局特征表示，在训练过程中可以监督注意擦除分支的训练。注意擦除局部分支由注意模块和擦除模块组成，该分支将输入特征映射的同一区域随机地分批擦除，以增强局部区域的注意特征学习；其次，在训练阶段采用标签平滑损失函数和三元组损失函数对模型进行联合训练。标签平滑损失函数用于防止分类任务过度拟合，三元组损失函数用于解决类间相似、类内差异的分类问题；最后，在Market-1501,DukeMTMC-reID两个数据集上、和现有的八种方法进行对比测试实验，rank-1/mAP分别达到94.3%/85.9%,87.2%/75.3%,优于其他现有方法。

关键词(KeyWords)： 行人重识别;特征表示;局部擦除;标签平滑损失;三元组损失

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(51375132);; 山西省自然科学基金(201801D121134)

作者(Author): 贺南南,张荣国,王晓,李建伟,胡静

参考文献(References)：

• [1] 罗浩，姜伟，范星，等.基于深度学习的行人重识别研究进展[J].自动化学报，2019,45(11):2032-2049.
• [2] CHEN D P,XU D,LI H S,et al.Group consistent similarity learning via deep crf for person re-identification[C]// Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:8649-8658.
• [3] SHEN Y T,LI H S,XIAO T,et al.Deep group-shuffling random walk for person re-identification[C]// Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:2265-2274.
• [4] SUN Y F,ZHENG L,YANG Y,et al.Beyond part models:Person retrieval with refined part pooling[C]// European Conference on Computer Vision.Munich:Springer,2018:501-518.
• [5] CHEN X S,FU C M,ZHAO Y,et al.Salience-Guided Cascaded Suppression Network for Person Re-identification[C]// Computer Vision and Pattern Recognition.Seattle:IEEE,2020:3300-3310.
• [6] MIAO J X,WU Y,LIU P,et al.Pose-Guided Feature Alignment for Occluded Person Re-Identification[C]// International Conference on Computer Vision.Seoul:IEEE,2019:542-551.
• [7] ZHENG L,HUANG Y J,LU H C,et al.Pose invariant embedding for deep person re-identification[J].IEEE Transactions on Image Processing,2019,28(9):4500-4509.
• [8] LI W,ZHU X T,GONG S G.Harmonious attention network for person re-identification[C]// Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:2285-2294.
• [9] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]// Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016:770-778.
• [10] TAY C P,ROY S,YAP K H.AANet:Attribute Attention Network for Person Re-Identifications[C]// Computer Vision and Pattern Recognition.Long Beach:IEEE,2019:7127-7136.
• [11] ZHONG Z,ZHENG L,CAO D,et al.Re-ranking person re-identification with k-reciprocal encoding[C]// Computer Vision and Pattern Recognition,Honolulu:IEEE,2017:3652-3661.
• [12] ZHENG Z D,ZHENG L,YANG Y.A discriminatively learned cnn embedding for person re-identification[J].ACM Trans on Multimedia Computing Communications and Applications,2017,14(1):13.
• [13] SZEGEDY C,VANHOUCKE V,IOFFE S,et al,Rethinking the inception architecture for computer vision[C]//Computer Vision and Pattern Recognition,Las Vegas:IEEE,2016:2818-2826.
• [14] ALEXANDER H,LUCAS B,BASTIAN L.In defense of the triplet loss for person re-identification[J].arXiv:2017,1703:07737.
• [15] ZHENG L,SHEN L Y,TIAN L,et al.Scalable person re-identification:a benchmark[C]// International Conference on Computer Vision.Santiago:IEEE,2015:1116-1124.
• [16] RISTANI E,SOIERA F,ZOU R,et al.Performance measures and a data set for multi-target,multicamera tracking[C]// European Conference on Computer Vision.Cham:Springer,2016:17-35.
• [17] FELZENSZWALB P F,GIRSHICK R B,MCALLESTER D,et al.Object Detection with Discriminatively Trained Part-Based Models[J],IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1627-1645.
• [18] WANG Y,WANG L,YOU Y,et al.Resource Aware Person Re-identification across Multiple Resolutions[C]// Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:8042-8051.
• [19] SHEN Y T,LI H S,YI S,et al.Person re-identification with deep similarity-guided graph neural network[C]// European Conference on Computer Vision,Munich:Springer,2018:508-526.
• [20] HOU R B,MA B P,CHANG H,et al.Interaction-and-aggregation network for person re-identification[C]// Computer Vision and Pattern Recognition,Long Beach:IEEE,2019:9317-9326.