Robust Pseudo-label Learning with Neighbor Relation for Unsupervised Visible-Infrared Person Re-Identification
Open Access
- 28 October 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2242-2251
Abstract
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 code is available at https://github.com/XiangboYin/RPNR.Keywords
All Related Versions
This publication has 39 references indexed in Scilit:
- Robust Object Re-identification with Coupled Noisy LabelsInternational Journal of Computer Vision, 2024
- Multi-view Information Integration and Propagation for occluded person re-identificationInformation Fusion, 2023
- Cluster Contrast for Unsupervised Person Re-identification2023
- Visible-Infrared Person Re-Identification Using Privileged Intermediate Information2023
- Neighborhood Collective Estimation for Noisy Label Identification and Correction2022
- Optimal Transport for Label-Efficient Visible-Infrared Person Re-Identification2022
- Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification2021
- Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-identification2020
- Probabilistic End-To-End Noise Correction for Learning With Noisy Labels2019
- Joint Optimization Framework for Learning with Noisy Labels2018