# Unsupervised Person Re-identification with Stochastic Training Strategy

arXiv: https://arxiv.org/abs/2108.06938 · HTML: https://mlsanity.com/paper/2108.06938/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 60 references that are in the map.
- First posted on arXiv 16 Aug 2021.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [A Survey on Contrastive Self-supervised Learning](https://mlsanity.com/paper/2011.00362/) (2020)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [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)
- [Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID](https://mlsanity.com/paper/2006.02713/) (2020)
- [Local Aggregation for Unsupervised Learning of Visual Embeddings](https://mlsanity.com/paper/1903.12355/) (2019)
- [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)
- [ABD-Net: Attentive but Diverse Person Re-Identification](https://mlsanity.com/paper/1908.01114/) (2019)
- [Relation-Aware Global Attention for Person Re-identification](https://mlsanity.com/paper/1904.02998/) (2019)
- [Unsupervised Person Re-identification via Multi-label Classification](https://mlsanity.com/paper/2004.09228/) (2020)
- [Dissecting Person Re-identification from the Viewpoint of Viewpoint](https://mlsanity.com/paper/1812.02162/) (2018)
- [Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification](https://mlsanity.com/paper/1910.12278/) (2019)
- [Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification](https://mlsanity.com/paper/2007.10315/) (2020)
- [AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2004.08787/) (2020)
- [Unsupervised Person Re-identification via Softened Similarity Learning](https://mlsanity.com/paper/2004.03547/) (2020)
- [ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification](https://mlsanity.com/paper/2103.16364/) (2021)
- [Camera Style Adaptation for Person Re-identification](https://mlsanity.com/paper/1711.10295/) (2017)
- [Camera-aware Proxies for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2012.10674/) (2020)
- [Group-aware Label Transfer for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2103.12366/) (2021)
- [Multiple Expert Brainstorming for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2007.01546/) (2020)
- [Unsupervised Person Re-identification by Soft Multilabel Learning](https://mlsanity.com/paper/1903.06325/) (2019)
- [IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2108.02413/) (2021)

## Built on by (most cited first, 7 of 7)

- [Multi-Query Video Retrieval](https://mlsanity.com/paper/2201.03639/) (2022)
- [Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification](https://mlsanity.com/paper/2201.05820/) (2022)
- [Image-Text-Image Knowledge Transfer for Lifelong Person Re-Identification with Hybrid Clothing States](https://mlsanity.com/paper/2405.16600/) (2024)
- [Large-scale Fully-Unsupervised Re-Identification](https://mlsanity.com/paper/2307.14278/) (2023)
- [Mutual Information Guided Optimal Transport for Unsupervised Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2407.12758/) (2024)
- [Domain-adaptive Person Re-identification without Cross-camera Paired Samples](https://mlsanity.com/paper/2307.06533/) (2023)
- [A review of Recent Techniques for Person Re-Identification](https://mlsanity.com/paper/2509.22690/) (2025)

## Abstract (arXiv)

Unsupervised person re-identification (re-ID) has attracted increasing research interests because of its scalability and possibility for real-world applications. State-of-the-art unsupervised re-ID methods usually follow a clustering-based strategy, which generates pseudo labels by clustering and maintains a memory to store instance features and represent the centroid of the clusters for contrastive learning. This approach suffers two problems. First, the centroid generated by unsupervised learning may not be a perfect prototype. Forcing images to get closer to the centroid emphasizes the result of clustering, which could accumulate clustering errors during iterations. Second, previous methods utilize features obtained at different training iterations to represent one centroid, which is not consistent with the current training sample, since the features are not directly comparable. To this end, we propose an unsupervised re-ID approach with a stochastic learning strategy. Specifically, we adopt a stochastic updated memory, where a random instance from a cluster is used to update the cluster-level memory for contrastive learning. In this way, the relationship between randomly selected pair of images are learned to avoid the training bias caused by unreliable pseudo labels. The stochastic memory is also always up-to-date for classifying to keep the consistency. Besides, to relieve the issue of camera variance, a unified distance matrix is proposed during clustering, where the distance bias from different camera domain is reduced and the variances of identities is emphasized.