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

TL;DR

This paper presents a simple yet effective baseline for person re-identification that combines various training tricks, achieving state-of-the-art performance with minimal complexity.

Contribution

It systematically collects and evaluates effective training tricks for deep person ReID, establishing a strong baseline with simple global features.

Findings

Achieves 94.5% rank-1 accuracy on Market1501

Achieves 85.9% mAP on Market1501

Demonstrates the effectiveness of combined training tricks

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.