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

Code

• github.com/michuanhaohao/reid-strong-baseline
  OfficialIn paperpytorch★ 2,334
• github.com/layumi/Person_reID_baseline_pytorch
  pytorch★ 4,415
• github.com/wenyu1009/pganet
  pytorch★ 9
• github.com/seominseok0429/vidoe_tracking-Reidentification-Action_recognition_Demo
  none★ 7
• github.com/zion-king/Deep-Learning-for-Person-Re-identification
  pytorch★ 2
• github.com/PaddlePaddle/PaddleClas/blob/release/2.5/docs/zh_CN/algorithm_introduction/ReID.md
  paddle★ 0
• github.com/bastiennNB/Pair_ReID
  pytorch★ 0
• github.com/lulujianjie/person-reid-tiny-baseline
  pytorch★ 0

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.

Tasks

Benchmark Results

Reproductions