CASIA OpenIR  > 智能感知与计算研究中心
Adversarially Occluded Samples for Person Re-identification
Huang HJ(黄厚景)1,2,3,4,5; Li DW(李党伟)1,2,3,4,5; Zhang Z(张彰)1,2,3,4,5; Chen XT(陈晓棠)1,2,3,4,5; Huang KQ(黄凯奇)1,2,3,4,5
2018-06-18
会议名称IEEE Conference on Computer Vision and Pattern Recognition
会议日期June 18-22, 2018
会议地点Salt Lake City, Utah, United States
摘要Person re-identification (ReID) is the task of retrieving particular persons across different cameras. Despite its great progress in recent years, it is still confronted with challenges like pose variation, occlusion, and similar appearance among different persons. The large gap between training and testing performance with existing models implies the insufficiency of generalization. Considering this fact, we propose to augment the variation of training data by introducing Adversarially Occluded Samples. These special samples are both a) meaningful in that they resemble real-scene occlusions, and b) effective in that they are tough for the original model and thus provide the momentum to jump out of local optimum. We mine these samples based on a trained ReID model and with the help of network visualization techniques. Extensive experiments show that the proposed samples help the model discover new discriminative clues on the body and generalize much better at test time. Our strategy makes significant improvement over strong baselines on three large-scale ReID datasets, Market1501, CUHK03 and DukeMTMC-reID.
关键词Person Re-identification Adversarial Occlusion 行人再识别 对抗 遮挡
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/22079
专题智能感知与计算研究中心
作者单位1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.CAS Center for Excellence in Brain Science and Intelligence Technology
4.National Laboratory of Pattern Recognition
5.Center for Research on Intelligent Perception and Computing
推荐引用方式
GB/T 7714
Huang HJ,Li DW,Zhang Z,et al. Adversarially Occluded Samples for Person Re-identification[C],2018.
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
Huang_Adversarially_(963KB)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
[Huang HJ(黄厚景)]的文章
[Li DW(李党伟)]的文章
[Zhang Z(张彰)]的文章
百度学术
百度学术中相似的文章
[Huang HJ(黄厚景)]的文章
[Li DW(李党伟)]的文章
[Zhang Z(张彰)]的文章
必应学术
必应学术中相似的文章
[Huang HJ(黄厚景)]的文章
[Li DW(李党伟)]的文章
[Zhang Z(张彰)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Huang_Adversarially_Occluded_Samples_CVPR_2018_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。