# Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification

arXiv: https://arxiv.org/abs/2206.06607 · HTML: https://mlsanity.com/paper/2206.06607/

## Key facts

- Cited by 2 papers in the map (data through 7 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 14 Jun 2022.

## Builds on (most cited first, 22 of 22)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [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)
- [Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection](https://mlsanity.com/paper/1903.07256/) (2019)
- [ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification](https://mlsanity.com/paper/2103.16364/) (2021)
- [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)
- [Linkage Based Face Clustering via Graph Convolution Network](https://mlsanity.com/paper/1903.11306/) (2019)
- [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)
- [Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification](https://mlsanity.com/paper/2012.08733/) (2020)
- [Learning to Cluster Faces via Confidence and Connectivity Estimation](https://mlsanity.com/paper/2004.00445/) (2020)
- [Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification](https://mlsanity.com/paper/1912.01349/) (2019)
- [Structure-Aware Face Clustering on a Large-Scale Graph with bf107 Nodes](https://mlsanity.com/paper/2103.13225/) (2021)
- [Towards Discriminative Representation Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2108.03439/) (2021)
- [Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification](https://mlsanity.com/paper/2108.09682/) (2021)
- [MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification](https://mlsanity.com/paper/2110.05886/) (2021)
- [Learn to Propagate Reliably on Noisy Affinity Graphs](https://mlsanity.com/paper/2007.08802/) (2020)

## Built on by (most cited first, 2 of 2)

- [AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models](https://mlsanity.com/paper/2511.20325/) (2025)
- [Unsupervised Visible-Infrared ReID via Pseudo-label Correction and Modality-level Alignment](https://mlsanity.com/paper/2404.06683/) (2024)

## Abstract (arXiv)

Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised learning (USL) and unsupervised domain adaptive (UDA) person re-identification (Re-ID). To alleviate the adverse effect of noisy pseudo labels, the existing methods either abandon unreliable labels or refine the pseudo labels via mutual learning or label propagation. However, a great many erroneous labels are still accumulated because these methods mostly adopt traditional unsupervised clustering algorithms which rely on certain assumptions on data distribution and fail to capture the distribution of complex real-world data. In this paper, we propose the plug-and-play graph-based pseudo label correction network (GLC) to refine the pseudo labels in the manner of supervised clustering. GLC is trained to perceive the varying data distribution at each epoch of the self-training with the supervision of initial pseudo labels generated by any clustering method. It can learn to rectify the initial noisy labels by means of the relationship constraints between samples on the k Nearest Neighbor (kNN) graph and early-stop training strategy. Specifically, GLC learns to aggregate node features from neighbors and predict whether the nodes should be linked on the graph. Besides, GLC is optimized with 'early stop' before the noisy labels are severely memorized to prevent overfitting to noisy pseudo labels. Consequently, GLC improves the quality of pseudo labels though the supervision signals contain some noise, leading to better Re-ID performance. Extensive experiments in USL and UDA person Re-ID on Market-1501 and MSMT17 show that our method is widely compatible with various clustering-based methods and promotes the state-of-the-art performance consistently.