# Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification

arXiv: https://arxiv.org/abs/1708.08062 · HTML: https://mlsanity.com/paper/1708.08062/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2017.

## Built on by (most cited first, 26 of 26)

- [Are These the Same Apple? Comparing Images Based on Object Intrinsics](https://mlsanity.com/paper/2311.00750/) (2023)
- [Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2106.07846/) (2021)
- [DeepChange: A Large Long-Term Person Re-Identification Benchmark with Clothes Change](https://mlsanity.com/paper/2105.14685/) (2021)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2109.12333/) (2021)
- [Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2207.13035/) (2022)
- [Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification](https://mlsanity.com/paper/2201.05820/) (2022)
- [Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions](https://mlsanity.com/paper/2109.06057/) (2021)
- [Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering](https://mlsanity.com/paper/2103.04580/) (2021)
- [Label a Herd in Minutes: Individual Holstein-Friesian Cattle Identification](https://mlsanity.com/paper/2204.10905/) (2022)
- [Multi-modal Multi-platform Person Re-Identification: Benchmark and Method](https://mlsanity.com/paper/2503.17096/) (2025)
- [Dual-Stream Reciprocal Disentanglement Learning for Domain Adaptation Person Re-Identification](https://mlsanity.com/paper/2106.13929/) (2021)
- [Few-shot Learning in Emotion Recognition of Spontaneous Speech Using a Siamese Neural Network with Adaptive Sample Pair Formation](https://mlsanity.com/paper/2109.02915/) (2021)
- [Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification](https://mlsanity.com/paper/2201.11995/) (2022)
- [Handling Label Uncertainty for Camera Incremental Person Re-Identification](https://mlsanity.com/paper/2210.08710/) (2022)
- [On the Applicability of Synthetic Data for Re-Identification](https://mlsanity.com/paper/2212.10105/) (2022)
- [Unsupervised Domain Adaptive Person Re-id with Local-enhance and Prototype Dictionary Learning](https://mlsanity.com/paper/2201.03803/) (2022)
- [Generalizable Re-Identification from Videos with Cycle Association](https://mlsanity.com/paper/2211.03663/) (2022)
- [Rank Flow Embedding for Unsupervised and Semi-Supervised Manifold Learning](https://mlsanity.com/paper/2304.12448/) (2023)
- [Person Re-ID through Unsupervised Hypergraph Rank Selection and Fusion](https://mlsanity.com/paper/2304.14321/) (2023)
- [CORE-ReID: Comprehensive Optimization and Refinement through Ensemble fusion in Domain Adaptation for person re-identification](https://mlsanity.com/paper/2508.03064/) (2025)
- [Unsupervised Noisy Tracklet Person Re-identification](https://mlsanity.com/paper/2101.06391/) (2021)
- [Hard Samples Rectification for Unsupervised Cross-domain Person Re-identification](https://mlsanity.com/paper/2106.07204/) (2021)
- [Discriminative-Region Attention and Orthogonal-View Generation Model for Vehicle Re-Identification](https://mlsanity.com/paper/2204.13323/) (2022)
- [Illumination Variation Correction Using Image Synthesis For Unsupervised Domain Adaptive Person Re-Identification](https://mlsanity.com/paper/2301.09702/) (2023)
- [On the Effectiveness of Heterogeneous Ensemble Methods for Re-identification](https://mlsanity.com/paper/2403.12606/) (2024)

## Abstract (arXiv)

While metric learning is important for Person re-identification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires quantities of labeled samples in all pairs of camera views for training. However, this limits their scalabilities to realistic applications, in which a large amount of data over multiple disjoint camera views is available but not labelled. To overcome the problem, we propose unsupervised asymmetric metric learning for unsupervised RE-ID. Our model aims to learn an asymmetric metric, i.e., specific projection for each view, based on asymmetric clustering on cross-view person images. Our model finds a shared space where view-specific bias is alleviated and thus better matching performance can be achieved. Extensive experiments have been conducted on a baseline and five large-scale RE-ID datasets to demonstrate the effectiveness of the proposed model. Through the comparison, we show that our model works much more suitable for unsupervised RE-ID compared to classical unsupervised metric learning models. We also compare with existing unsupervised RE-ID methods, and our model outperforms them with notable margins. Specifically, we report the results on large-scale unlabelled RE-ID dataset, which is important but unfortunately less concerned in literatures.