Identity Clue Refinement and Enhancement for Visible-Infrared Person Re-Identification

TL;DR

This paper introduces a novel network for visible-infrared person re-identification that leverages modality-specific attributes and identity-aware knowledge to improve cross-modal matching accuracy.

Contribution

The paper proposes the ICRE network with MPFR and SDCE modules, effectively utilizing modality-specific features and identity knowledge for better re-identification.

Findings

ICRE outperforms existing state-of-the-art methods on multiple datasets.

The MPFR module captures overlooked modality-specific attributes.

The SDCE module distills identity-aware knowledge to enhance feature discrimination.

Abstract

Visible-Infrared Person Re-Identification (VI-ReID) is a challenging cross-modal matching task due to significant modality discrepancies. While current methods mainly focus on learning modality-invariant features through unified embedding spaces, they often focus solely on the common discriminative semantics across modalities while disregarding the critical role of modality-specific identity-aware knowledge in discriminative feature learning. To bridge this gap, we propose a novel Identity Clue Refinement and Enhancement (ICRE) network to mine and utilize the implicit discriminative knowledge inherent in modality-specific attributes. Initially, we design a Multi-Perception Feature Refinement (MPFR) module that aggregates shallow features from shared branches, aiming to capture modality-specific attributes that are easily overlooked. Then, we propose a Semantic Distillation Cascade Enhancement (SDCE) module, which distills identity-aware knowledge from the aggregated shallow features and guide the learning of modality-invariant features. Finally, an Identity Clues Guided (ICG) Loss is proposed to alleviate the modality discrepancies within the enhanced features and promote the learning of a diverse representation space. Extensive experiments across multiple public datasets clearly show that our proposed ICRE outperforms existing SOTA methods.