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

arXiv: https://arxiv.org/abs/1906.08332 · HTML: https://mlsanity.com/paper/1906.08332/

## Key facts

- Cited by 155 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2019.

## Built on by (most cited first, 30 of 155)

- [StrongSORT: Make DeepSORT Great Again](https://mlsanity.com/paper/2202.13514/) (2022)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking](https://mlsanity.com/paper/2308.00783/) (2023)
- [Part-based Pseudo Label Refinement for Unsupervised Person Re-identification](https://mlsanity.com/paper/2203.14675/) (2022)
- [Group-aware Label Transfer for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2103.12366/) (2021)
- [Text-Based Person Search with Limited Data](https://mlsanity.com/paper/2110.10807/) (2021)
- [Intra-Inter Camera Similarity for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11658/) (2021)
- [IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2108.02413/) (2021)
- [Neural Feature Search for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2104.02366/) (2021)
- [GiT: Graph Interactive Transformer for Vehicle Re-identification](https://mlsanity.com/paper/2107.05475/) (2021)
- [PLIP: Language-Image Pre-training for Person Representation Learning](https://mlsanity.com/paper/2305.08386/) (2023)
- [On the Unreasonable Effectiveness of Centroids in Image Retrieval](https://mlsanity.com/paper/2104.13643/) (2021)
- [Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification](https://mlsanity.com/paper/2107.02380/) (2021)
- [Learning a Proposal Classifier for Multiple Object Tracking](https://mlsanity.com/paper/2103.07889/) (2021)
- [Large-Scale Pre-training for Person Re-identification with Noisy Labels](https://mlsanity.com/paper/2203.16533/) (2022)
- [GPGait: Generalized Pose-based Gait Recognition](https://mlsanity.com/paper/2303.05234/) (2023)
- [Self-Supervised Pre-Training for Transformer-Based Person Re-Identification](https://mlsanity.com/paper/2111.12084/) (2021)
- [MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering](https://mlsanity.com/paper/2203.09138/) (2022)
- [Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting](https://mlsanity.com/paper/2107.03576/) (2021)
- [Modality Unifying Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2309.06262/) (2023)
- [Lifelong Person Re-Identification via Knowledge Refreshing and Consolidation](https://mlsanity.com/paper/2211.16201/) (2022)
- [Heterogeneous Relational Complement for Vehicle Re-identification](https://mlsanity.com/paper/2109.07894/) (2021)
- [Explainable Person Re-Identification with Attribute-guided Metric Distillation](https://mlsanity.com/paper/2103.01451/) (2021)
- [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024)
- [SFANet: A Spectrum-aware Feature Augmentation Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2102.12137/) (2021)
- [City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones](https://mlsanity.com/paper/2105.06623/) (2021)
- [1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking](https://mlsanity.com/paper/2101.08040/) (2021)
- [DeepChange: A Large Long-Term Person Re-Identification Benchmark with Clothes Change](https://mlsanity.com/paper/2105.14685/) (2021)
- [Quality-aware Part Models for Occluded Person Re-identification](https://mlsanity.com/paper/2201.00107/) (2022)
- [Multi-spectral Vehicle Re-identification with Cross-directional Consistency Network and a High-quality Benchmark](https://mlsanity.com/paper/2208.00632/) (2022)

## Abstract (arXiv)

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.