Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification

TL;DR

This paper introduces Hi-CMD, a hierarchical disentanglement approach for visible-infrared person re-identification, effectively reducing intra- and cross-modality discrepancies to improve matching accuracy in night-time surveillance.

Contribution

The paper proposes a novel hierarchical disentanglement framework with an ID-preserving generation network and feature learning module for VI-ReID, addressing both intra- and cross-modality challenges.

Findings

Outperforms state-of-the-art on two VI-ReID datasets

Effective disentanglement of ID-discriminative and ID-excluded factors

Robust cross-modality matching under varying poses and illuminations

Abstract

Visible-infrared person re-identification (VI-ReID) is an important task in night-time surveillance applications, since visible cameras are difficult to capture valid appearance information under poor illumination conditions. Compared to traditional person re-identification that handles only the intra-modality discrepancy, VI-ReID suffers from additional cross-modality discrepancy caused by different types of imaging systems. To reduce both intra- and cross-modality discrepancies, we propose a Hierarchical Cross-Modality Disentanglement (Hi-CMD) method, which automatically disentangles ID-discriminative factors and ID-excluded factors from visible-thermal images. We only use ID-discriminative factors for robust cross-modality matching without ID-excluded factors such as pose or illumination. To implement our approach, we introduce an ID-preserving person image generation network and a hierarchical feature learning module. Our generation network learns the disentangled representation by generating a new cross-modality image with different poses and illuminations while preserving a person's identity. At the same time, the feature learning module enables our model to explicitly extract the common ID-discriminative characteristic between visible-infrared images. Extensive experimental results demonstrate that our method outperforms the state-of-the-art methods on two VI-ReID datasets. The source code is available at: https://github.com/bismex/HiCMD.