# Robust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification

arXiv: https://arxiv.org/abs/2405.05613 · HTML: https://mlsanity.com/paper/2405.05613/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 9 May 2024.

## Builds on (most cited first, 7 of 7)

- [Camera-aware Proxies for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2012.10674/) (2020)
- [TOP-ReID: Multi-spectral Object Re-Identification with Token Permutation](https://mlsanity.com/paper/2312.09612/) (2023)
- [Salvage Reusable Samples from Noisy Data for Robust Learning](https://mlsanity.com/paper/2008.02427/) (2020)
- [Multi-Centroid Representation Network for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2112.11689/) (2021)
- [Multi-view Information Integration and Propagation for Occluded Person Re-identification](https://mlsanity.com/paper/2311.03828/) (2023)
- [Unsupervised Visible-Infrared Person ReID by Collaborative Learning with Neighbor-Guided Label Refinement](https://mlsanity.com/paper/2305.12711/) (2023)
- [ProtoHPE: Prototype-guided High-frequency Patch Enhancement for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2310.07552/) (2023)

## Built on by (most cited first, 10 of 10)

- [Cross-video Identity Correlating for Person Re-identification Pre-training](https://mlsanity.com/paper/2409.18569/) (2024)
- [Unity is Strength: Unifying Convolutional and Transformeral Features for Better Person Re-Identification](https://mlsanity.com/paper/2412.17239/) (2024)
- [LATex: Leveraging Attribute-based Text Knowledge for Aerial-Ground Person Re-Identification](https://mlsanity.com/paper/2503.23722/) (2025)
- [Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification](https://mlsanity.com/paper/2507.01884/) (2025)
- [Relieving Universal Label Noise for Unsupervised Visible-Infrared Person Re-Identification by Inferring from Neighbors](https://mlsanity.com/paper/2412.12220/) (2024)
- [Weakly Supervised Visible-Infrared Person Re-Identification via Heterogeneous Expert Collaborative Consistency Learning](https://mlsanity.com/paper/2507.12942/) (2025)
- [Causal Bootstrapped Alignment for Unsupervised Video-Based Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2604.15631/) (2026)
- [Hierarchical Identity Learning for Unsupervised Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2509.11587/) (2025)
- [Bridging Day and Night: Unsupervised Cross-Domain Re-Identification with Synergistic Prompt and Prototype Learning](https://mlsanity.com/paper/2606.12258/) (2026)
- [SCORE: SubDistribution-aware Collaborative Knowledge Reinforcing for Cloth-Hybrid Lifelong Person Re-Identification](https://mlsanity.com/paper/2609.12577/) (2026)

## Abstract (arXiv)

Unsupervised Visible-Infrared Person Re-identification (USVI-ReID) presents a formidable challenge, which aims to match pedestrian images across visible and infrared modalities without any annotations. Recently, clustered pseudo-label methods have become predominant in USVI-ReID, although the inherent noise in pseudo-labels presents a significant obstacle. Most existing works primarily focus on shielding the model from the harmful effects of noise, neglecting to calibrate noisy pseudo-labels usually associated with hard samples, which will compromise the robustness of the model. To address this issue, we design a Robust Pseudo-label Learning with Neighbor Relation (RPNR) framework for USVI-ReID. To be specific, we first introduce a straightforward yet potent Noisy Pseudo-label Calibration module to correct noisy pseudo-labels. Due to the high intra-class variations, noisy pseudo-labels are difficult to calibrate completely. Therefore, we introduce a Neighbor Relation Learning module to reduce high intra-class variations by modeling potential interactions between all samples. Subsequently, we devise an Optimal Transport Prototype Matching module to establish reliable cross-modality correspondences. On that basis, we design a Memory Hybrid Learning module to jointly learn modality-specific and modality-invariant information. Comprehensive experiments conducted on two widely recognized benchmarks, SYSU-MM01 and RegDB, demonstrate that RPNR outperforms the current state-of-the-art GUR with an average Rank-1 improvement of 10.3%. The source codes will be released soon.