MRCN: A Novel Modality Restitution and Compensation Network for Visible-Infrared Person Re-identification

TL;DR

This paper introduces MRCN, a new network for visible-infrared person re-identification that effectively reduces cross-modality discrepancies by disentangling and restoring modality-specific features, leading to state-of-the-art results.

Contribution

The paper proposes a novel MRCN architecture with modules for modality restitution and compensation, and a new CQC loss to improve modality-invariant feature learning.

Findings

Achieves 95.1% Rank-1 accuracy on RegDB dataset.

Outperforms existing methods on SYSU-MM01 and RegDB datasets.

Demonstrates effective disentanglement of modality-relevant and irrelevant features.

Abstract

Visible-infrared person re-identification (VI-ReID), which aims to search identities across different spectra, is a challenging task due to large cross-modality discrepancy between visible and infrared images. The key to reduce the discrepancy is to filter out identity-irrelevant interference and effectively learn modality-invariant person representations. In this paper, we propose a novel Modality Restitution and Compensation Network (MRCN) to narrow the gap between the two modalities. Specifically, we first reduce the modality discrepancy by using two Instance Normalization (IN) layers. Next, to reduce the influence of IN layers on removing discriminative information and to reduce modality differences, we propose a Modality Restitution Module (MRM) and a Modality Compensation Module (MCM) to respectively distill modality-irrelevant and modality-relevant features from the removed information. Then, the modality-irrelevant features are used to restitute to the normalized visible and infrared features, while the modality-relevant features are used to compensate for the features of the other modality. Furthermore, to better disentangle the modality-relevant features and the modality-irrelevant features, we propose a novel Center-Quadruplet Causal (CQC) loss to encourage the network to effectively learn the modality-relevant features and the modality-irrelevant features. Extensive experiments are conducted to validate the superiority of our method on the challenging SYSU-MM01 and RegDB datasets. More remarkably, our method achieves 95.1% in terms of Rank-1 and 89.2% in terms of mAP on the RegDB dataset.