Bag of Tricks and a Strong Baseline for Deep Person Re-Identification

Hao Luo, Youzhi Gu, Xingyu Liao, Shenqi Lai, Wei Jiang

CVPRW 2019 pp. 1487-1495

doi:10.1109/CVPRW.2019.00190 /cvprw/2019/luo2019cvprw-bag/

Abstract

This paper explores a simple and efficient baseline for person re-identification (ReID). Person re-identification (ReID) with deep neural networks has made progress and achieved high performance in recent years. However, many state-of-the-arts methods design complex network structure and concatenate multi-branch features. In the literature, some effective training tricks are briefly appeared in several papers or source codes. This paper will collect and evaluate these effective training tricks in person ReID. By combining these tricks together, the model achieves 94.5% rank-1 and 85.9% mAP on Market1501 with only using global features. Our codes and models are available at https://github.com/michuanhaohao/reid-strong-baseline.

PDF CVPRW Semantic Scholar

Cite

Text

Luo et al. "Bag of Tricks and a Strong Baseline for Deep Person Re-Identification." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00190

Markdown

[Luo et al. "Bag of Tricks and a Strong Baseline for Deep Person Re-Identification." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/luo2019cvprw-bag/) doi:10.1109/CVPRW.2019.00190

BibTeX

@inproceedings{luo2019cvprw-bag,
  title     = {{Bag of Tricks and a Strong Baseline for Deep Person Re-Identification}},
  author    = {Luo, Hao and Gu, Youzhi and Liao, Xingyu and Lai, Shenqi and Jiang, Wei},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2019},
  pages     = {1487-1495},
  doi       = {10.1109/CVPRW.2019.00190},
  url       = {https://mlanthology.org/cvprw/2019/luo2019cvprw-bag/}
}