# Large-Scale Unsupervised Person Re-Identification with Contrastive Learning

arXiv: https://arxiv.org/abs/2105.07914 · HTML: https://mlsanity.com/paper/2105.07914/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 17 May 2021.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Towards Real-Time Multi-Object Tracking](https://mlsanity.com/paper/1909.12605/) (2019)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification](https://mlsanity.com/paper/2001.01526/) (2020)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID](https://mlsanity.com/paper/2006.02713/) (2020)
- [Person Re-identification: Past, Present and Future](https://mlsanity.com/paper/1610.02984/) (2016)
- [Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification](https://mlsanity.com/paper/1711.07027/) (2017)
- [Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/1904.01990/) (2019)
- [Unsupervised Person Re-identification via Multi-label Classification](https://mlsanity.com/paper/2004.09228/) (2020)
- [Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification](https://mlsanity.com/paper/1910.12278/) (2019)
- [Unsupervised Person Re-identification via Softened Similarity Learning](https://mlsanity.com/paper/2004.03547/) (2020)
- [Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification](https://mlsanity.com/paper/1803.09786/) (2018)
- [Unsupervised Tracklet Person Re-Identification](https://mlsanity.com/paper/1903.00535/) (2019)
- [Unsupervised Person Re-identification by Deep Learning Tracklet Association](https://mlsanity.com/paper/1809.02874/) (2018)
- [CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions](https://mlsanity.com/paper/2007.07577/) (2020)
- [Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.04618/) (2021)
- [Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding](https://mlsanity.com/paper/1901.10177/) (2019)
- [Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification](https://mlsanity.com/paper/1912.01300/) (2019)
- [Intra-Camera Supervised Person Re-Identification: A New Benchmark](https://mlsanity.com/paper/1908.10344/) (2019)

## Built on by (most cited first, 2 of 2)

- [Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2308.08887/) (2023)
- [Generalizable Re-Identification from Videos with Cycle Association](https://mlsanity.com/paper/2211.03663/) (2022)

## Abstract (arXiv)

Existing public person Re-Identification~(ReID) datasets are small in modern terms because of labeling difficulty. Although unlabeled surveillance video is abundant and relatively easy to obtain, it is unclear how to leverage these footage to learn meaningful ReID representations. In particular, most existing unsupervised and domain adaptation ReID methods utilize only the public datasets in their experiments, with labels removed. In addition, due to small data sizes, these methods usually rely on fine tuning by the unlabeled training data in the testing domain to achieve good performance. Inspired by the recent progress of large-scale self-supervised image classification using contrastive learning, we propose to learn ReID representation from large-scale unlabeled surveillance video alone. Assisted by off-the-shelf pedestrian detection tools, we apply the contrastive loss at both the image and the tracklet levels. Together with a principal component analysis step using camera labels freely available, our evaluation using a large-scale unlabeled dataset shows far superior performance among unsupervised methods that do not use any training data in the testing domain. Furthermore, the accuracy improves with the data size and therefore our method has great potential with even larger and more diversified datasets.