Deep person re-identification with improved embedding and efficient training

@article{Jin2017DeepPR,
  title={Deep person re-identification with improved embedding and efficient training},
  author={Haibo Jin and Xiaobo Wang and Shengcai Liao and Stan Z. Li},
  journal={2017 IEEE International Joint Conference on Biometrics (IJCB)},
  year={2017},
  pages={261-267}
}
Person re-identification task has been greatly boosted by deep convolutional neural networks (CNNs) in recent years. The core of which is to enlarge the inter-class distinction as well as reduce the intra-class variance. However, to achieve this, existing deep models prefer to adopt image pairs or triplets to form verification loss, which is inefficient and unstable since the number of training pairs or triplets grows rapidly as the number of training data grows. Moreover, their performance is… CONTINUE READING