Deep Feature Embedding Learning for Person Re-Identification Using Lifted Structured Loss

Zhangping He; Zhendong Zhang; Cheolkon Jung

ICASSP 2018accepted0 citations

Deep Feature Embedding Learning for Person Re-Identification Using Lifted Structured Loss

Zhangping He, Zhendong Zhang, Cheolkon Jung

Abstract

In this paper, we propose deep feature embedding learning for person re-identification (re-id) using lifted structured loss. Although triplet loss has been commonly used in deep neural networks for person re-id, the triplet loss-based framework is not effective in fully using the batch information. Thus, it needs to choose hard negative samples manually that is very time-consuming. To address this problem, we adopt lifted structured loss for deep neural networks that makes the network learn better feature embedding by minimizing intra-class variation and maximizing inter-class variation. Extensive experiments on CUHK03, CUHKOI and VIPeR datasets demonstrate the superior performance of the proposed method over state-of-the-arts in terms of the cumulative match curve (CMC) metric.

BibTeX

@inproceedings{icassp2018_deepfeatureembed,
  title = {Deep Feature Embedding Learning for Person Re-Identification Using Lifted Structured Loss},
  author = {Zhangping He and Zhendong Zhang and Cheolkon Jung},
  booktitle = {ICASSP 2018},
  year = {2018}
}