# Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identification

arXiv: https://arxiv.org/abs/2112.14025 · HTML: https://mlsanity.com/paper/2112.14025/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 46 references that are in the map.
- First posted on arXiv 28 Dec 2021.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2003.03773/) (2020)
- [Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification](https://mlsanity.com/paper/2001.01526/) (2020)
- [DLOW: Domain Flow for Adaptation and Generalization](https://mlsanity.com/paper/1812.05418/) (2018)
- [Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification](https://mlsanity.com/paper/1711.07027/) (2017)
- [A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification](https://mlsanity.com/paper/1906.08332/) (2019)
- [Data Uncertainty Learning in Face Recognition](https://mlsanity.com/paper/2003.11339/) (2020)
- [Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/1904.01990/) (2019)
- [Cross-Batch Memory for Embedding Learning](https://mlsanity.com/paper/1912.06798/) (2019)
- [Gradually Vanishing Bridge for Adversarial Domain Adaptation](https://mlsanity.com/paper/2003.13183/) (2020)
- [Unsupervised Person Re-identification via Multi-label Classification](https://mlsanity.com/paper/2004.09228/) (2020)
- [AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2004.08787/) (2020)
- [Unsupervised Person Re-identification: Clustering and Fine-tuning](https://mlsanity.com/paper/1705.10444/) (2017)
- [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)
- [Self-training with progressive augmentation for unsupervised cross-domain person re-identification](https://mlsanity.com/paper/1907.13315/) (2019)
- [MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.13575/) (2021)
- [Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification](https://mlsanity.com/paper/1910.10111/) (2019)
- [Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification](https://mlsanity.com/paper/2012.08733/) (2020)
- [Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation](https://mlsanity.com/paper/1909.09675/) (2019)
- [Multi-Target Domain Adaptation with Collaborative Consistency Learning](https://mlsanity.com/paper/2106.03418/) (2021)
- [Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification](https://mlsanity.com/paper/1912.01349/) (2019)
- [A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification](https://mlsanity.com/paper/1904.03425/) (2019)
- [Global Distance-distributions Separation for Unsupervised Person Re-identification](https://mlsanity.com/paper/2006.00752/) (2020)
- [Real-world Person Re-Identification via Degradation Invariance Learning](https://mlsanity.com/paper/2004.04933/) (2020)

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

- [Lifelong Person Re-Identification via Knowledge Refreshing and Consolidation](https://mlsanity.com/paper/2211.16201/) (2022)
- [BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation](https://mlsanity.com/paper/2403.15019/) (2024)
- [Robust Duality Learning for Unsupervised Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2505.02549/) (2025)
- [Learning Feature Fusion for Unsupervised Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2205.09495/) (2022)
- [Domain-adaptive Person Re-identification without Cross-camera Paired Samples](https://mlsanity.com/paper/2307.06533/) (2023)
- [Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification](https://mlsanity.com/paper/2406.14797/) (2024)
- [AIDA-ReID: Adaptive Intermediate Domain Adaptation for Generalizable and Source-Free Person Re-Identification](https://mlsanity.com/paper/2605.00111/) (2026)

## Abstract (arXiv)

Clustering-based unsupervised domain adaptive (UDA) person re-identification (ReID) reduces exhaustive annotations. However, owing to unsatisfactory feature embedding and imperfect clustering, pseudo labels for target domain data inherently contain an unknown proportion of wrong ones, which would mislead feature learning. In this paper, we propose an approach named probabilistic uncertainty guided progressive label refinery (P2LR) for domain adaptive person re-identification. First, we propose to model the labeling uncertainty with the probabilistic distance along with ideal single-peak distributions. A quantitative criterion is established to measure the uncertainty of pseudo labels and facilitate the network training. Second, we explore a progressive strategy for refining pseudo labels. With the uncertainty-guided alternative optimization, we balance between the exploration of target domain data and the negative effects of noisy labeling. On top of a strong baseline, we obtain significant improvements and achieve the state-of-the-art performance on four UDA ReID benchmarks. Specifically, our method outperforms the baseline by 6.5% mAP on the Duke2Market task, while surpassing the state-of-the-art method by 2.5% mAP on the Market2MSMT task.