Bag of Tricks and a Strong Baseline for Deep Person Re-Identification

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.

Keywords

Baseline (sea)Computer scienceIdentification (biology)Artificial intelligenceRank (graph theory)Deep learningArtificial neural networkDeep neural networksMachine learningMathematics

Affiliated Institutions

Related Publications

Harmonious Attention Network for Person Re-identification

Wei Li , Xiatian Zhu , Shaogang Gong

Existing person re-identification (re-id) methods either assume the availability of well-aligned person bounding box images as model input or rely on constrained attention selec...

2018 1377 citations

Person Transfer GAN to Bridge Domain Gap for Person Re-identification

Longhui Wei , Shiliang Zhang , Wen Gao +1 more

Although the performance of person Re-Identification (ReID) has been significantly boosted, many challenging issues in real scenarios have not been fully investigated, e.g., the...

2018 2018 IEEE/CVF Conference on Computer ... 1899 citations

Learning to rank in person re-identification with metric ensembles

Sakrapee Paisitkriangkrai , Chunhua Shen , Anton van den Hengel

We propose an effective structured learning based approach to the problem of person re-identification which outperforms the current state-of-the-art on most benchmark data sets ...

2015 arXiv (Cornell University) 55 citations

Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)

Yifan Sun , Liang Zheng , Yi Yang +2 more

Employing part-level features for pedestrian image description offers fine-grained information and has been verified as beneficial for person retrieval in very recent literature...

2018 Lecture notes in computer science 2482 citations

Deep Learning for Person Re-Identification: A Survey and Outlook

Mang Ye , Jianbing Shen , Gaojie Lin +3 more

Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. With the advancement of deep neural networks and increasing dem...

2021 IEEE Transactions on Pattern Analysis... 1875 citations

Publication Info

Year: 2019
Type: article
Citations: 1346
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Bag of Tricks and a Strong Baseline for Deep Person Re-Identification

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1346

OpenAlex

Cite This

APA Style

                            
                                    Hao Luo, 
                                
                                    Youzhi Gu, 
                                
                                    Xingyu Liao
                                
                                et al.
                            
                            (2019). 
                            Bag of Tricks and a Strong Baseline for Deep Person Re-Identification. 
                            
                            .
                            https://doi.org/10.1109/cvprw.2019.00190

Identifiers

DOI: 10.1109/cvprw.2019.00190