基于相关性得分的伪标签优化行人重识别
CSTR:
作者:
作者单位:

1. 中国矿业大学 信息与控制工程学院,江苏 徐州 221116;2. 中国矿业大学 计算机科学与技术学院,江苏 徐州 221116

作者简介:

通讯作者:

E-mail: chengdq@cumt.edu.cn.

中图分类号:

TP391

基金项目:

国家自然科学基金项目(52204177).


Person re-identification with pseudo label refinement based on correlation score
Author:
Affiliation:

1. School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221116,China;2. School of Computer Science and Technology,China University of Mining and Technology,Xuzhou 221116,China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    无监督域自适应行人重识别旨在将源域训练的识别能力泛化到目标域上,以减少对标签的依赖.目前基于聚类方法的网络,聚类过程中不可避免地会受到环境噪声的影响,降低网络原有识别性能.为了解决这一问题,提出一种基于相关性得分的伪标签优化行人重识别网络.首先,通过计算全局与局部特征间前k个相似样本集合的相关性得分,找到两类特征直接可靠的关联性,从而提取已有伪标签优化方法所忽略的局部细粒度特征;然后,利用得分对局部伪标签进行优化处理,降低网络对与行人无关局部特征的关注;最后,依赖于相关性得分,利用优化后局部伪标签的预测结果对全局伪标签进行细化,缓解聚类过程中噪声的同时也细化了行人的特征完整表示.与近年无监督域自适应行人重识别方法相比,所提出网络在DukeMTMC-ReID、Market1501和MSMT17三个公开数据集上的实验结果表现优异,验证了所提出网络的有效性.

    Abstract:

    The purpose of unsupervised domain adaptive person re-identification is to generalize the recognition ability of training in the source domain to the target domain to reduce the dependence on labels. At present, the network based on clustering methods will inevitably be affected by environmental noise during the clustering process, which will reduce the original recognition performance of the network. To solve this problem, the person re-identification network with pseudo label refinement based on correlation score is proposed. Firstly, by calculating the correlation scores between the top k similar sample sets of global and local features, reliable correlations between two types of features are found, so as to extract local fine-grained features that existing pseudo-label optimization methods ignore. Then, the scores are used to optimize the local pseudo-labels, reducing the network's attention to irrelevant local features of the person. In addition, relying on the correlation scores, the prediction results of the optimized local pseudo-labels are used to refine the global pseudo-labels, which alleviates noise during the clus-tering process and refines the complete representation of person features. Compared with the unsupervised domain adaptive method in recent years, the experimental results of the network on three public data sets, DukeMTMC-ReID, Market1501 and MSMT17, show that the network performance is significantly improved.

    参考文献
    相似文献
    引证文献
引用本文

程德强,黄绩,寇旗旗,等.基于相关性得分的伪标签优化行人重识别[J].控制与决策,2024,39(8):2579-2587

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2024-07-16
  • 出版日期: 2024-08-20
文章二维码