Bag of Tricks and A Strong Baseline for Deep Person Re-identification

Hao Luo, Youzhi Gu, Xingyu Liao, Shenqi Lai, Wei Jiang
3/17/2019
cs.CV

Official code: michuanhaohao/reid-strong-baseline (2,357 stars, MIT, last commit 2020-04-23).

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.

View on arXivView PDF

Code Implementations(1)

michuanhaohao/reid-strong-baselineOfficial100%
MIT

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

2,357580Shell, PythonMar 16, 20196 years agoMIT

Similar Papers

A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification

96% match1 repo2.4k2019

Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training

87% match1 repo112024

Ranking and Classification driven Feature Learning for Person Re_identification

87% match1 repo1002019

Deep Learning for Person Re-identification: A Survey and Outlook

86% match1 repo7542020

A Discriminatively Learned CNN Embedding for Person Re-identification

86% match1 repo2642016

End-to-End Deep Kronecker-Product Matching for Person Re-identification

86% match1 repo1032018

Cite this paper

@article{luo2019tricks,
  title  = {Bag of Tricks and A Strong Baseline for Deep Person Re-identification},
  author = {Hao Luo and Youzhi Gu and Xingyu Liao and Shenqi Lai and Wei Jiang},
  year   = {2019},
  eprint = {1903.07071},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1903.07071}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1903.07071.svg)](https://codeofpaper.com/paper/1903.07071)

Discussion