Adversarially Occluded Samples for Person Re-identification
文献类型：会议论文
| 作者 | 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; Huang, Kaiqi(黄凯奇); Huang, Houjing(黄厚景); Li, Dangwei(李党伟); Zhang, Zhang(张彰); Chen, Xiaotang(陈晓棠)
|
| 出版日期 | 2018-06-18 |
| 会议日期 | June 18-22, 2018 |
| 会议地点 | Salt Lake City, Utah, United States |
| 关键词 | Person Re-identification Adversarial Occlusion 行人再识别 对抗 遮挡 |
| 英文摘要 | 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. |
| 语种 | 英语 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/22079]  |
| 专题 | 自动化研究所_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]. 见:. Salt Lake City, Utah, United States. June 18-22, 2018. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。