Cross-Modal Distillation for RGB-Depth Person Re-Identification

TL;DR

This paper introduces a novel cross-modal distillation method for person re-identification between RGB and depth images, significantly improving accuracy by learning shared features and employing a cross-modal attention mechanism.

Contribution

The paper proposes a new cross-modal distillation approach and a cross-modal attention mechanism for robust RGB-depth person re-identification, outperforming existing methods.

Findings

Achieved up to 16.1% improvement in mAP over state-of-the-art.

Cross-modal attention enhances recognition accuracy.

Method outperforms conventional approaches on BIWI and RobotPKU datasets.

Abstract

Person re-identification is a key challenge for surveillance across multiple sensors. Prompted by the advent of powerful deep learning models for visual recognition, and inexpensive RGB-D cameras and sensor-rich mobile robotic platforms, e.g. self-driving vehicles, we investigate the relatively unexplored problem of cross-modal re-identification of persons between RGB (color) and depth images. The considerable divergence in data distributions across different sensor modalities introduces additional challenges to the typical difficulties like distinct viewpoints, occlusions, and pose and illumination variation. While some work has investigated re-identification across RGB and infrared, we take inspiration from successes in transfer learning from RGB to depth in object detection tasks. Our main contribution is a novel method for cross-modal distillation for robust person re-identification, which learns a shared feature representation space of person's appearance in both RGB and depth images. In addition, we propose a cross-modal attention mechanism where the gating signal from one modality can dynamically activate the most discriminant CNN filters of the other modality. The proposed distillation method is compared to conventional and deep learning approaches proposed for other cross-domain re-identification tasks. Results obtained on the public BIWI and RobotPKU datasets indicate that the proposed method can significantly outperform the state-of-the-art approaches by up to 16.1% in mean Average Precision (mAP), demonstrating the benefit of the distillation paradigm. The experimental results also indicate that using cross-modal attention allows to improve recognition accuracy considerably with respect to the proposed distillation method and relevant state-of-the-art approaches.