综述:
Person Re-identification_ Past, Present and Future
基于深度学习的行人重识别研究进展-罗浩
网络:
PCB:
Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
MGN:
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
损失函数:
Triplet Loss:
Deep feature learning with relative distance comparison for person re-identification
TriHard Loss:
In Defense of the Triplet Loss for Person Re-Identification.2017
Quadruplet Loss:
Beyond triplet loss: a deep quadruplet network for person re-identification.2017
Margin Sample Mining Loss(MSML):
Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification.2017
数据集:
MSMT17:
Person Transfer GAN to Bridge Domain Gap for Person Re-Identification