# Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification

arXiv: https://arxiv.org/abs/2012.13689 · HTML: https://mlsanity.com/paper/2012.13689/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Dec 2020.

## Built on by (most cited first, 25 of 25)

- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Group-aware Label Transfer for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2103.12366/) (2021)
- [IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2108.02413/) (2021)
- [Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification](https://mlsanity.com/paper/2108.09682/) (2021)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Unsupervised Visible-Infrared Person ReID by Collaborative Learning with Neighbor-Guided Label Refinement](https://mlsanity.com/paper/2305.12711/) (2023)
- [Learning to Purification for Unsupervised Person Re-identification](https://mlsanity.com/paper/2204.09931/) (2022)
- [Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation](https://mlsanity.com/paper/2108.03372/) (2021)
- [Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification](https://mlsanity.com/paper/2203.15210/) (2022)
- [Unsupervised Person Re-identification with Stochastic Training Strategy](https://mlsanity.com/paper/2108.06938/) (2021)
- [Unsupervised and self-adaptative techniques for cross-domain person re-identification](https://mlsanity.com/paper/2103.11520/) (2021)
- [Rethinking Sampling Strategies for Unsupervised Person Re-identification](https://mlsanity.com/paper/2107.03024/) (2021)
- [Primitive3D: 3D Object Dataset Synthesis from Randomly Assembled Primitives](https://mlsanity.com/paper/2205.12627/) (2022)
- [Learning Feature Fusion for Unsupervised Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2205.09495/) (2022)
- [A Survey of Historical Learning: Learning Models with Learning History](https://mlsanity.com/paper/2303.12992/) (2023)
- [Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains](https://mlsanity.com/paper/2203.01682/) (2022)
- [From Indoor To Outdoor: Unsupervised Domain Adaptive Gait Recognition](https://mlsanity.com/paper/2211.11155/) (2022)
- [DDAM-PS: Diligent Domain Adaptive Mixer for Person Search](https://mlsanity.com/paper/2310.20706/) (2023)
- [Pseudo-label Refinement for Improving Self-Supervised Learning Systems](https://mlsanity.com/paper/2410.14242/) (2024)
- [CORE-ReID: Comprehensive Optimization and Refinement through Ensemble fusion in Domain Adaptation for person re-identification](https://mlsanity.com/paper/2508.03064/) (2025)
- [Dynamic Clustering and Cluster Contrastive Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2303.06810/) (2023)
- [Domain-adaptive Person Re-identification without Cross-camera Paired Samples](https://mlsanity.com/paper/2307.06533/) (2023)
- [REPAIR: Rank Correlation and Noisy Pair Half-replacing with Memory for Noisy Correspondence](https://mlsanity.com/paper/2403.08224/) (2024)
- [Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification](https://mlsanity.com/paper/2406.14797/) (2024)
- [CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion](https://mlsanity.com/paper/2508.04036/) (2025)

## Abstract (arXiv)

Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a challenging task due to the missing of labels for the target domain data. To handle this problem, some recent works adopt clustering algorithms to off-line generate pseudo labels, which can then be used as the supervision signal for on-line feature learning in the target domain. However, the off-line generated labels often contain lots of noise that significantly hinders the discriminability of the on-line learned features, and thus limits the final UDA re-ID performance. To this end, we propose a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase, to alternatively boost the label purity and feature discriminability in the target domain for more reliable re-ID. Specifically, at the off-line phase, a new hierarchical clustering scheme is proposed, which selects representative prototypes for every coarse cluster. Thus, labels can be effectively refined by using the inherent hierarchical information of person images. Besides, at the on-line phase, we propose an instant memory spread-out (IM-spread-out) regularization, that takes advantage of the proposed instant memory bank to store sample features of the entire dataset and enable spread-out feature learning over the entire training data instantly. Our Dual-Refinement method reduces the influence of noisy labels and refines the learned features within the alternative training process. Experiments demonstrate that our method outperforms the state-of-the-art methods by a large margin.