# Unsupervised Pre-training for Person Re-identification

arXiv: https://arxiv.org/abs/2012.03753 · HTML: https://mlsanity.com/paper/2012.03753/

## Key facts

- Cited by 95 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2020.

## Built on by (most cited first, 30 of 95)

- [Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks](https://mlsanity.com/paper/2303.17602/) (2023)
- [PLIP: Language-Image Pre-training for Person Representation Learning](https://mlsanity.com/paper/2305.08386/) (2023)
- [Large-Scale Pre-training for Person Re-identification with Noisy Labels](https://mlsanity.com/paper/2203.16533/) (2022)
- [HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining](https://mlsanity.com/paper/2303.05675/) (2023)
- [DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations](https://mlsanity.com/paper/2208.08190/) (2022)
- [Self-Supervised Pre-Training for Transformer-Based Person Re-Identification](https://mlsanity.com/paper/2111.12084/) (2021)
- [Self-Supervised Learning via Maximum Entropy Coding](https://mlsanity.com/paper/2210.11464/) (2022)
- [HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception](https://mlsanity.com/paper/2310.20695/) (2023)
- [The One Where They Reconstructed 3D Humans and Environments in TV Shows](https://mlsanity.com/paper/2207.14279/) (2022)
- [Synthetic Data in Human Analysis: A Survey](https://mlsanity.com/paper/2208.09191/) (2022)
- [SoccerNet 2022 Challenges Results](https://mlsanity.com/paper/2210.02365/) (2022)
- [Position: Measure Dataset Diversity, Don't Just Claim It](https://mlsanity.com/paper/2407.08188/) (2024)
- [Learning Gait Representation from Massive Unlabelled Walking Videos: A Benchmark](https://mlsanity.com/paper/2206.13964/) (2022)
- [Hulk: A Universal Knowledge Translator for Human-Centric Tasks](https://mlsanity.com/paper/2312.01697/) (2023)
- [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024)
- [Adaptive Sparse Pairwise Loss for Object Re-Identification](https://mlsanity.com/paper/2303.18247/) (2023)
- [The 7th AI City Challenge](https://mlsanity.com/paper/2304.07500/) (2023)
- [Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification](https://mlsanity.com/paper/2309.01420/) (2023)
- [Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation](https://mlsanity.com/paper/2201.01297/) (2022)
- [DC-Former: Diverse and Compact Transformer for Person Re-Identification](https://mlsanity.com/paper/2302.14335/) (2023)
- [The 8th AI City Challenge](https://mlsanity.com/paper/2404.09432/) (2024)
- [Improve Unsupervised Pretraining for Few-label Transfer](https://mlsanity.com/paper/2107.12369/) (2021)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [A Versatile Framework for Multi-scene Person Re-identification](https://mlsanity.com/paper/2403.11121/) (2024)
- [Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2308.08887/) (2023)
- [Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification](https://mlsanity.com/paper/2112.00317/) (2021)
- [Learning to Purification for Unsupervised Person Re-identification](https://mlsanity.com/paper/2204.09931/) (2022)
- [Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification](https://mlsanity.com/paper/2310.17218/) (2023)
- [Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training](https://mlsanity.com/paper/2406.06045/) (2024)
- [SCAM! Transferring humans between images with Semantic Cross Attention Modulation](https://mlsanity.com/paper/2210.04883/) (2022)

## Abstract (arXiv)

In this paper, we present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson" and make the first attempt of performing unsupervised pre-training for improving the generalization ability of the learned person Re-ID feature representation. This is to address the problem that all existing person Re-ID datasets are all of limited scale due to the costly effort required for data annotation. Previous research tries to leverage models pre-trained on ImageNet to mitigate the shortage of person Re-ID data but suffers from the large domain gap between ImageNet and person Re-ID data. LUPerson is an unlabeled dataset of 4M images of over 200K identities, which is 30X larger than the largest existing Re-ID dataset. It also covers a much diverse range of capturing environments (eg, camera settings, scenes, etc.). Based on this dataset, we systematically study the key factors for learning Re-ID features from two perspectives: data augmentation and contrastive loss. Unsupervised pre-training performed on this large-scale dataset effectively leads to a generic Re-ID feature that can benefit all existing person Re-ID methods. Using our pre-trained model in some basic frameworks, our methods achieve state-of-the-art results without bells and whistles on four widely used Re-ID datasets: CUHK03, Market1501, DukeMTMC, and MSMT17. Our results also show that the performance improvement is more significant on small-scale target datasets or under few-shot setting.