Knowledge Commons of Institute of Automation,CAS
Proxy Task Learning for Cross-Domain Person Re-Identification | |
Huang, Houjing1,2; Chen, Xiaotang1,2; Huang, Kaiqi1,2,3 | |
2020-07 | |
会议名称 | IEEE International Conference on Multimedia and Expo (ICME) |
会议日期 | 2020.7.6-10 |
会议地点 | London, United Kingdom, United Kingdom |
摘要 | Person re-identification (ReID) has achieved rapid improvement recently. However, exploiting the model in a new scene is always faced with huge performance drop. The cause lies in distribution discrepancy between domains, including both low-level (e.g. image quality) and high-level (e.g. pedestrian attribute) variance. To alleviate the problem of domain shift, we propose a novel framework Proxy Task Learning (PTL), which performs body perception tasks on target-domain images while training source-domain ReID, in a multi-task manner. The backbone is shared between tasks and domains, hence both low- and high-level distributions are deeply aligned. We experimentally verify two proxy tasks, i.e. human parsing and attribute recognition, that prominently enhance generalization of the model. When integrating our method into an existing cross-domain pipeline, we achieve state-of-the-art performance on large-scale benchmarks. |
关键词 | Person Re-identification, Cross-domain, Multi-task, Human Parsing, Attribute Recognition |
收录类别 | EI |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/42209 |
专题 | 复杂系统认知与决策实验室_智能系统与工程 |
通讯作者 | Chen, Xiaotang |
作者单位 | 1.Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology |
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 | Huang, Houjing,Chen, Xiaotang,Huang, Kaiqi. Proxy Task Learning for Cross-Domain 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 | ||
Proxy Task Learning (1047KB) | 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