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

By Hao Luo, Wei Jiang, Youzhi Gu, Fuxu Liu, Xingyu Liao, Shenqi Lai, Jianyang Gu. IEEE transactions on multimedia, 2019

628 citations recorded by the source corpus.

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

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/557ba3d8f7bba0bbf00cf6363f3263484b541d6f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

StrongSORT: Make DeepSORT Great Again (2022, methodology): “In addition, a stronger appearance feature extractor, BoT [30], is applied to replace the original simple CNN, which can extract much more discriminative features.”
Rethinking the Competition Between Detection and ReID in Multiobject Tracking (2020, background): “, ReID network [6]) needs to perform forward inference for each individual bounding box.”
Channel Augmented Joint Learning for Visible-Infrared Recognition (2021, methodology): “Random erasing [59] has been widely evaluated on various vision tasks to improve the generalizability on testing task [25].”
Group-aware Label Transfer for Domain Adaptive Person Re-identification (2021, methodology): ““BOT” denotes to “bag of tricks” method [31], which is a strong baseline in the ReID task.”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “We also compare two state-of-the-art methods, BagTricks [151] and ABD-Net [137].”