Modality-Aware Bias Mitigation and Invariance Learning for Unsupervised Visible-Infrared Person Re-Identification

2025-12-08

AI Summary

To address unreliable cross-modal associations and significant modality bias in unsupervised visible-infrared person re-identification (USVI-ReID), this paper proposes a debiased global association framework. Methodologically, it introduces a modality-aware Jaccard distance to mitigate distribution discrepancies between visible and infrared features; designs a split-and-contrast strategy to construct modality-specific prototypes and achieves global instance-level clustering alignment via optimal transport; and jointly optimizes contrastive learning and prototype alignment to learn modality-invariant, identity-discriminative representations. The framework achieves state-of-the-art performance on mainstream benchmarks—including SYSU-MM01 and RegDB—demonstrating substantial improvements in cross-modal matching accuracy and robustness under fully unsupervised settings.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match individuals across visible and infrared cameras without relying on any annotation. Given the significant gap across visible and infrared modality, estimating reliable cross-modality association becomes a major challenge in USVI-ReID. Existing methods usually adopt optimal transport to associate the intra-modality clusters, which is prone to propagating the local cluster errors, and also overlooks global instance-level relations. By mining and attending to the visible-infrared modality bias, this paper focuses on addressing cross-modality learning from two aspects: bias-mitigated global association and modality-invariant representation learning. Motivated by the camera-aware distance rectification in single-modality re-ID, we propose modality-aware Jaccard distance to mitigate the distance bias caused by modality discrepancy, so that more reliable cross-modality associations can be estimated through global clustering. To further improve cross-modality representation learning, a `split-and-contrast' strategy is designed to obtain modality-specific global prototypes. By explicitly aligning these prototypes under global association guidance, modality-invariant yet ID-discriminative representation learning can be achieved. While conceptually simple, our method obtains state-of-the-art performance on benchmark VI-ReID datasets and outperforms existing methods by a significant margin, validating its effectiveness.

Problem

• Mitigates modality bias in unsupervised visible-infrared person re-identification.
• Improves global cross-modality association via clustering and distance rectification.
• Learns modality-invariant representations using prototype alignment and contrastive strategies.

Innovation

• Modality-aware Jaccard distance mitigates cross-modality bias
• Split-and-contrast strategy obtains modality-specific global prototypes
• Aligns prototypes globally for modality-invariant representation learning