| Fully Unsupervised Person Re-Identification by Enhancing Cluster Samples | |
Chen, Xiumei1,2; Zheng, Xiangtao1 ; Zhu, Kaijian3; Lu, Xiaoqiang1
| |
| 2021-12-16 | |
| 会议名称 | 7th International Conference on Communication and Information Processing, ICCIP 2021 |
| 会议录名称 | 2021 7th International Conference on Communication and Information Processing, ICCIP 2021 |
| 页码 | 70-73 |
| 会议日期 | 2021-12-16 |
| 会议地点 | Virtual, Online, China |
| 出版者 | Association for Computing Machinery |
| 产权排序 | 1 |
| 摘要 | Fully unsupervised person re-identification aims to train a discriminative model with unlabeled person images. Most existing methods first generate pseudo labels by clustering image features (convolutional features) and then fine-tune the convolutional neural network (CNN) with pseudo labels. However, these methods are greatly limited by the quality of the pseudo labels. In this paper, a cluster sample enhancement method is introduced to increase the reliability of pseudo-label samples to facilitate the CNN training. Specifically, when generating pseudo labels, only the samples with high-confidence pseudo-label predictions are selected. In addition, to enhance the selected samples for training, two different image transformations are adopted and coupled with specific-design loss functions to boost the model performance. Experiments demonstrate the effectiveness of the proposed method. Concretely, the proposed method achieves 87.1% rank-1 and 70.2% mAP accuracy on Market-1501. © 2021 ACM. |
| 关键词 | unsupervised person re-identification sample transformation convolutional neural network feature extraction |
| 作者部门 | 光谱成像技术研究室 |
| DOI | 10.1145/3507971.3507984 |
| 收录类别 | EI |
| ISBN号 | 9781450385190 |
| 语种 | 英语 |
| EI入藏号 | 20221311871695 |
| 引用统计 | |
| 文献类型 | 会议论文 |
| 条目标识符 | http://ir.opt.ac.cn/handle/181661/95804 |
| 专题 | 光谱成像技术研究室 |
| 作者单位 | 1.Key Laboratory of Spectral Imaging Technology CAS, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, Shaanxi, China; 2.University of Chinese Academy of Sciences Beijing, China; 3.State Key Laboratory of Astronautic Dynamics, Xi'an Satellite Control Center, Xi'an, Shaanxi, China |
| 推荐引用方式 GB/T 7714 | Chen, Xiumei,Zheng, Xiangtao,Zhu, Kaijian,et al. Fully Unsupervised Person Re-Identification by Enhancing Cluster Samples[C]:Association for Computing Machinery,2021:70-73. |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
| Fully Unsupervised P（532KB） | 会议论文 | 限制开放 | CC BY-NC-SA | 请求全文 | ||
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