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

19 Jun 2019  ·  Hao Luo, Wei Jiang, Youzhi Gu, Fuxu Liu, Xingyu Liao, Shenqi Lai, Jianyang Gu ·

This study explores a simple but strong baseline for person re-identification (ReID). Person ReID with deep neural networks has progressed and achieved 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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Person Re-Identification DukeMTMC-reID ReID strong baseline (IBN-Net50-a) Rank-1 90.1 # 28
mAP 79.1 # 38
Person Re-Identification Market-1501 IBN-Net50-a mAP 88.2 # 47

Methods