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

This study proposes a simple but strong baseline for deep person re-identification (ReID). Deep person ReID has achieved great progress and high performance in recent years. However, many state-of-the-art methods design complex network structures and concatenate multi-branch features. In the literat...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia 2020-10, Vol.22 (10), p.2597-2609
Main Authors: Luo, Hao, Jiang, Wei, Gu, Youzhi, Liu, Fuxu, Liao, Xingyu, Lai, Shenqi, Gu, Jianyang
Format: Article
Language:English
Subjects:
baseline
BNNeck
Computational modeling
deep learning
Feature extraction
Gallium nitride
Measurement
Neck
Performance enhancement
Person ReID
Task analysis
Training
tricks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study proposes a simple but strong baseline for deep person re-identification (ReID). Deep person ReID has achieved great progress and high performance in recent years. However, many state-of-the-art methods design complex network structures and concatenate multi-branch features. In the literature, some effective training tricks briefly appear in several papers or source codes. The present study collects and evaluates these effective training tricks in person ReID. By combining these tricks, the model achieves 94.5% rank-1 and 85.9% mean average precision on Market1501 with only using the global features of ResNet50. The performance surpasses all existing global- and part-based baselines in person ReID. We propose a novel neck structure named as batch normalization neck (BNNeck). BNNeck adds a batch normalization layer after global pooling layer to separate metric and classification losses into two different feature spaces because we observe they are inconsistent in one embedding space. Extended experiments show that BNNeck can boost the baseline, and our baseline can improve the performance of existing state-of-the-art methods. Our codes and models are available at: https://github.com/michuanhaohao/reid-strong-baseline
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2019.2958756