AVPL: Augmented Visual Perception Learning for Person Re-identification and Beyond

论文题目:

AVPL: Augmented Visual Perception Learning for Person Re-identification and Beyond

论文基于人类视觉理论提出增强视觉感知学习方法,在行人重识别上取得了较大的进展,实验结果rank-1 accuracy of 95.2% on CUHK03-NP, 98.7% on Market-1501, 96.0% on DukeMTMC-reID and 88.8% on MSMT17, outperforming the state-of-the-art methods by a large margin.

AVPL: Augmented Visual Perception Learning for Person Re-identification and Beyond

  • 实验结果

  • CUHK03-NP

AVPL: Augmented Visual Perception Learning for Person Re-identification and Beyond

AVPL: Augmented Visual Perception Learning for Person Re-identification and Beyond

  • Market-1501

AVPL: Augmented Visual Perception Learning for Person Re-identification and Beyond