Clothing-Change Feature Augmentation for Person Re-Identification | |
Ke, Han1,2; Shaogang, Gong3; Yan, Huang1,2; Liang, Wang1,2; Tieniu, Tan1,2,4 | |
2023-06 | |
会议名称 | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition |
卷号 | 22066 |
会议日期 | 2023.6.18-2023.6.22 |
会议地点 | 加拿大温哥华 |
摘要 | Clothing-change person re-identification (CC Re-ID) aims to match the same person who changes clothes across cameras. Current methods are usually limited by the insufficient number and variation of clothing in training data, e.g. each person only has 2 outfits in the PRCC dataset. In this work, we propose a novel Clothing-Change Feature Augmentation (CCFA) model for CC Re-ID to largely expand clothing-change data in the feature space rather than visual image space. It automatically models the feature distribution expansion that reflects a person's clothing colour and texture variations to augment model training. Specifically, to formulate meaningful clothing variations in the feature space, our method first estimates a clothing-change normal distribution with intra-ID cross-clothing variances. Then an augmentation generator learns to follow the estimated distribution to augment plausible clothing-change features. The augmented features are guaranteed to maximise the change of clothing and minimise the change of identity properties by adversarial learning to assure the effectiveness. Such augmentation is performed iteratively with an ID-correlated augmentation strategy to increase intra-ID clothing variations and reduce inter-ID clothing variations, enforcing the Re-ID model to learn clothing-independent features inherently. Extensive experiments demonstrate the effectiveness of our method with state-of-the-art results on CC Re-ID datasets. |
收录类别 | EI |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52194 |
专题 | 模式识别实验室 |
通讯作者 | Yan, Huang |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences (CASIA) 2.University of Chinese Academy of Sciences (UCAS) 3.Queen Mary University of London (QMUL) 4.Nanjing University |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Ke, Han,Shaogang, Gong,Yan, Huang,et al. Clothing-Change Feature Augmentation for Person Re-Identification[C],2023. |
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 | ||
CVPR 2023.pdf(1001KB) | 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