Deep Top-rank Counter Metric for Person Re-identification | |
Chen Chen1; Hao Dou1; Xiyuan Hu2; Silong Peng1,3 | |
2020-12 | |
会议名称 | International Conference on Pattern Recognition |
会议日期 | 2021-1 |
会议地点 | Milan, Italy |
摘要 | In the research field of person re-identification, deep metric learning that guides the efficient and effective embedding learning serves as one of the most fundamental tasks. Recent efforts of the loss function based deep metric learning methods mainly focus on the top rank accuracy optimization by minimizing the distance difference between the correctly matching sample pair and wrongly matched sample pair. However, it is more straightforward to count the occurrences of correct top-rank candidates and maximize the counting results for better top rank accuracy. In this paper, we propose a generalized logistic function based metric with effective practicalness in deep learning, namely the“deep top-rank counter metric”, to approximately optimize the counted occurrences of the correct top-rank matches. The properties that qualify the proposed metric as a well-suited deep re-identification metric have been discussed and a progressive hard sample mining strategy is also introduced for effective training and performance boosting. The extensive experiments show that the proposed top-rank counter metric outperforms other loss function based deep metrics and achieves the state-of-the-art accuracies. |
关键词 | person re-identification metric learning top-rank counter deep learning |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 机器学习 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44772 |
专题 | 智能制造技术与系统研究中心_多维数据分析(彭思龙)-技术团队 |
通讯作者 | Chen Chen |
作者单位 | 1.Institude of Automation,Chinese Academy of Sciences 2.Nanjing University of Science and Technology 3.Institude of Automation,Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Chen Chen,Hao Dou,Xiyuan Hu,et al. Deep Top-rank Counter Metric for Person Re-identification[C],2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
7-ChenChen-ICPR-2020(766KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论