Joint Discriminative and Generative Learning for Person Re-identification

CVPR 2019 Zhedong ZhengXiaodong YangZhiding YuLiang ZhengYi YangJan Kautz

Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. Recently, there has been a growing interest in using generative models to augment training data and enhance the invariance to input changes... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Person Re-Identification CUHK03 DG-Net MAP 61.1 # 3
Person Re-Identification DukeMTMC-reID DG-Net(RK) Rank-1 90.26 # 4
Person Re-Identification DukeMTMC-reID DG-Net(RK) MAP 88.31 # 4
Person Re-Identification DukeMTMC-reID DG-Net Rank-1 86.6 # 11
Person Re-Identification DukeMTMC-reID DG-Net MAP 74.8 # 11
Person Re-Identification Market-1501 DG-Net(RK) Rank-1 95.40 # 7
Person Re-Identification Market-1501 DG-Net(RK) MAP 92.49 # 5
Person Re-Identification Market-1501 DG-Net Rank-1 94.8 # 9
Person Re-Identification Market-1501 DG-Net MAP 86.0 # 13
Person Re-Identification MSMT17 DG-Net Rank-1 77.2 # 4
Person Re-Identification MSMT17 DG-Net mAP 52.3 # 3