CASIA OpenIR  > 智能感知与计算研究中心
Beyond triplet loss: a deep quadruplet network for person re-identification
Weihua Chen1; Xiaotang Chen1; Jianguo Zhang2; Kaiqi Huang1
2017
会议名称IEEE Computer Vision and Pattern Recognition (CVPR)
会议日期2017-7-21
会议地点Hawaii, USA
摘要Person re-identification (ReID) is an important task in wide area video surveillance which focuses on identifying people across different cameras. Recently, deep learning networks with a triplet loss become a common framework for person ReID. However, the triplet loss pays main attentions on obtaining correct orders on the training set. It still suffers from a weaker generalization capability from the training set to the testing set, thus resulting in inferior performance. In this paper, we design a quadruplet loss, which can lead to the model output with a larger inter-class variation and a smaller intra-class variation compared to the triplet loss. As a result, our model has a better generalization ability and can achieve a higher performance on the testing set. In particular, a quadruplet deep network using a margin-based online hard negative mining is proposed based on the quadruplet loss for the person ReID. In extensive experiments, the proposed network outperforms most of the state-of-the-art algorithms on representative datasets which clearly demonstrates the effectiveness of our proposed method.
收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/19644
专题智能感知与计算研究中心
作者单位1.中国科学院自动化研究所
2.英国邓迪大学
推荐引用方式
GB/T 7714
Weihua Chen,Xiaotang Chen,Jianguo Zhang,et al. Beyond triplet loss: a deep quadruplet network for person re-identification[C],2017.
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
Chen_Beyond_Triplet_(1122KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Weihua Chen]的文章
[Xiaotang Chen]的文章
[Jianguo Zhang]的文章
百度学术
百度学术中相似的文章
[Weihua Chen]的文章
[Xiaotang Chen]的文章
[Jianguo Zhang]的文章
必应学术
必应学术中相似的文章
[Weihua Chen]的文章
[Xiaotang Chen]的文章
[Jianguo Zhang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Chen_Beyond_Triplet_Loss_CVPR_2017_paper.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。