Base-Detail Feature Learning Framework for Visible-Infrared Person Re-Identification

2025-05-06

AI Summary

To address the significant modality gap and neglect of modality-specific details in visible-infrared person re-identification (VI-ReID), this paper proposes a Base-Detail Dual-Path Feature Learning framework. First, a complementary base embedding mechanism models modality-shared discriminative features. Second, a lossless detail extraction module preserves modality-specific structural information. Additionally, a cross-modal correlation constraint loss is introduced to explicitly enforce complementarity between the base and detail features. Extensive experiments on three major benchmarks—SYSU-MM01, RegDB, and LLCM—demonstrate that our method achieves state-of-the-art performance, significantly improving both robustness and accuracy for 24-hour cross-modal matching.

Technology Category

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

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
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Visible-infrared person re-identification (VIReID) provides a solution for ReID tasks in 24-hour scenarios; however, significant challenges persist in achieving satisfactory performance due to the substantial discrepancies between visible (VIS) and infrared (IR) modalities. Existing methods inadequately leverage information from different modalities, primarily focusing on digging distinguishing features from modality-shared information while neglecting modality-specific details. To fully utilize differentiated minutiae, we propose a Base-Detail Feature Learning Framework (BDLF) that enhances the learning of both base and detail knowledge, thereby capitalizing on both modality-shared and modality-specific information. Specifically, the proposed BDLF mines detail and base features through a lossless detail feature extraction module and a complementary base embedding generation mechanism, respectively, supported by a novel correlation restriction method that ensures the features gained by BDLF enrich both detail and base knowledge across VIS and IR features. Comprehensive experiments conducted on the SYSU-MM01, RegDB, and LLCM datasets validate the effectiveness of BDLF.

Problem

• Addresses visible-infrared modality discrepancies in person re-identification
• Enhances learning of both shared and specific modality features
• Proposes a framework to mine detail and base features effectively

Innovation

• Lossless detail feature extraction module
• Complementary base embedding generation mechanism
• Correlation restriction method for feature enrichment