# Global Distance-distributions Separation for Unsupervised Person Re-identification

arXiv: https://arxiv.org/abs/2006.00752 · HTML: https://mlsanity.com/paper/2006.00752/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2020.

## Built on by (most cited first, 24 of 24)

- [Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization](https://mlsanity.com/paper/2103.15537/) (2021)
- [Group-aware Label Transfer for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2103.12366/) (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)
- [Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold](https://mlsanity.com/paper/2209.06209/) (2022)
- [Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.04618/) (2021)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation](https://mlsanity.com/paper/2103.11661/) (2021)
- [Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions](https://mlsanity.com/paper/2109.06057/) (2021)
- [Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identification](https://mlsanity.com/paper/2112.14025/) (2021)
- [Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering](https://mlsanity.com/paper/2103.04580/) (2021)
- [Meta Clustering Learning for Large-scale Unsupervised Person Re-identification](https://mlsanity.com/paper/2111.10032/) (2021)
- [Population-Based Evolutionary Gaming for Unsupervised Person Re-identification](https://mlsanity.com/paper/2306.05236/) (2023)
- [Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters](https://mlsanity.com/paper/2110.07897/) (2021)
- [A formal approach to good practices in Pseudo-Labeling for Unsupervised Domain Adaptive Re-Identification](https://mlsanity.com/paper/2112.12887/) (2021)
- [TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification](https://mlsanity.com/paper/2112.14239/) (2021)
- [Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains](https://mlsanity.com/paper/2203.01682/) (2022)
- [Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning](https://mlsanity.com/paper/2403.10252/) (2024)
- [Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2103.13917/) (2021)
- [Unsupervised Domain Generalization for Person Re-identification: A Domain-specific Adaptive Framework](https://mlsanity.com/paper/2111.15077/) (2021)
- [Hard Samples Rectification for Unsupervised Cross-domain Person Re-identification](https://mlsanity.com/paper/2106.07204/) (2021)
- [Unsupervised Person Re-identification via Multi-Label Prediction and Classification based on Graph-Structural Insight](https://mlsanity.com/paper/2106.08798/) (2021)
- [Mind Your Clever Neighbours: Unsupervised Person Re-identification via Adaptive Clustering Relationship Modeling](https://mlsanity.com/paper/2112.01839/) (2021)
- [Dynamic Clustering and Cluster Contrastive Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2303.06810/) (2023)

## Abstract (arXiv)

Supervised person re-identification (ReID) often has poor scalability and usability in real-world deployments due to domain gaps and the lack of annotations for the target domain data. Unsupervised person ReID through domain adaptation is attractive yet challenging. Existing unsupervised ReID approaches often fail in correctly identifying the positive samples and negative samples through the distance-based matching/ranking. The two distributions of distances for positive sample pairs (Pos-distr) and negative sample pairs (Neg-distr) are often not well separated, having large overlap. To address this problem, we introduce a global distance-distributions separation (GDS) constraint over the two distributions to encourage the clear separation of positive and negative samples from a global view. We model the two global distance distributions as Gaussian distributions and push apart the two distributions while encouraging their sharpness in the unsupervised training process. Particularly, to model the distributions from a global view and facilitate the timely updating of the distributions and the GDS related losses, we leverage a momentum update mechanism for building and maintaining the distribution parameters (mean and variance) and calculate the loss on the fly during the training. Distribution-based hard mining is proposed to further promote the separation of the two distributions. We validate the effectiveness of the GDS constraint in unsupervised ReID networks. Extensive experiments on multiple ReID benchmark datasets show our method leads to significant improvement over the baselines and achieves the state-of-the-art performance.