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

TL;DR

This paper introduces a Base-Detail Feature Learning Framework (BDLF) for visible-infrared person re-identification, effectively capturing both shared and modality-specific features to improve cross-modal matching performance.

Contribution

The paper proposes a novel BDLF that extracts and utilizes both base and detail features, addressing limitations of existing methods that neglect modality-specific information.

Findings

BDLF outperforms existing methods on SYSU-MM01, RegDB, and LLCM datasets.

The correlation restriction enhances feature enrichment across modalities.

Experimental results demonstrate improved re-identification accuracy.

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.