Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences

TL;DR

This paper introduces a novel framework for visible-infrared person re-identification that leverages dense cross-modal correspondences to improve discriminative feature learning and address modality discrepancies.

Contribution

It proposes exploiting dense pixel-level correspondences between cross-modal images to enhance feature alignment and discrimination in VI-reID.

Findings

Significantly outperforms state-of-the-art methods on standard benchmarks.

Effectively suppresses modality-related features for better discrimination.

Addresses misalignment issues in person images for improved re-identification.

Abstract

We address the problem of visible-infrared person re-identification (VI-reID), that is, retrieving a set of person images, captured by visible or infrared cameras, in a cross-modal setting. Two main challenges in VI-reID are intra-class variations across person images, and cross-modal discrepancies between visible and infrared images. Assuming that the person images are roughly aligned, previous approaches attempt to learn coarse image- or rigid part-level person representations that are discriminative and generalizable across different modalities. However, the person images, typically cropped by off-the-shelf object detectors, are not necessarily well-aligned, which distract discriminative person representation learning. In this paper, we introduce a novel feature learning framework that addresses these problems in a unified way. To this end, we propose to exploit dense correspondences between cross-modal person images. This allows to address the cross-modal discrepancies in a pixel-level, suppressing modality-related features from person representations more effectively. This also encourages pixel-wise associations between cross-modal local features, further facilitating discriminative feature learning for VI-reID. Extensive experiments and analyses on standard VI-reID benchmarks demonstrate the effectiveness of our approach, which significantly outperforms the state of the art.