Spectral Enhancement and Pseudo-Anchor Guidance for Infrared-Visible Person Re-Identification

2024-12-26

AI Summary

To address the matching difficulty in infrared-visible cross-modal person re-identification caused by spectral discrepancies, this paper proposes a spectral enhancement mechanism that jointly operates in the frequency domain and grayscale space, effectively mitigating information loss during modality translation. Furthermore, we design a pseudo-anchor-guided bidirectional aggregation (PABA) loss to simultaneously align local features and enhance identity discriminability. Our method integrates dual-stream embedding learning with cross-modal feature alignment, enabling robust 24-hour cross-illumination person retrieval. Extensive experiments demonstrate state-of-the-art performance on the SYSU-MM01 and RegDB benchmarks, significantly outperforming existing approaches. The source code is publicly available.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

The development of deep learning has facilitated the application of person re-identification (ReID) technology in intelligent security. Visible-infrared person re-identification (VI-ReID) aims to match pedestrians across infrared and visible modality images enabling 24-hour surveillance. Current studies relying on unsupervised modality transformations as well as inefficient embedding constraints to bridge the spectral differences between infrared and visible images, however, limit their potential performance. To tackle the limitations of the above approaches, this paper introduces a simple yet effective Spectral Enhancement and Pseudo-anchor Guidance Network, named SEPG-Net. Specifically, we propose a more homogeneous spectral enhancement scheme based on frequency domain information and greyscale space, which avoids the information loss typically caused by inefficient modality transformations. Further, a Pseudo Anchor-guided Bidirectional Aggregation (PABA) loss is introduced to bridge local modality discrepancies while better preserving discriminative identity embeddings. Experimental results on two public benchmark datasets demonstrate the superior performance of SEPG-Net against other state-of-the-art methods. The code is available at https://github.com/1024AILab/ReID-SEPG.

Problem

• Cross-modal Human Recognition
• Infrared and Visible Light
• Lighting Variation Handling

Innovation

• SEPG-Net
• Visible-Infrared Person Re-Identification
• Information Retention Enhancement