Breaking Modality Gap in RGBT Tracking: Coupled Knowledge Distillation

TL;DR

This paper introduces CKD, a novel framework that reduces the modality gap between RGB and thermal images in tracking by style distillation and content decoupling, leading to improved accuracy and speed.

Contribution

The work proposes a coupled knowledge distillation approach with style-content decoupling and strategies for robustness and efficiency in RGBT tracking.

Findings

Outperforms state-of-the-art methods on five datasets.

Achieves the fastest tracking speed of 96.4 FPS.

Effectively reduces modality gap and improves tracking robustness.

Abstract

Modality gap between RGB and thermal infrared (TIR) images is a crucial issue but often overlooked in existing RGBT tracking methods. It can be observed that modality gap mainly lies in the image style difference. In this work, we propose a novel Coupled Knowledge Distillation framework called CKD, which pursues common styles of different modalities to break modality gap, for high performance RGBT tracking. In particular, we introduce two student networks and employ the style distillation loss to make their style features consistent as much as possible. Through alleviating the style difference of two student networks, we can break modality gap of different modalities well. However, the distillation of style features might harm to the content representations of two modalities in student networks. To handle this issue, we take original RGB and TIR networks as the teachers, and distill their content knowledge into two student networks respectively by the style-content orthogonal feature decoupling scheme. We couple the above two distillation processes in an online optimization framework to form new feature representations of RGB and thermal modalities without modality gap. In addition, we design a masked modeling strategy and a multi-modal candidate token elimination strategy into CKD to improve tracking robustness and efficiency respectively. Extensive experiments on five standard RGBT tracking datasets validate the effectiveness of the proposed method against state-of-the-art methods while achieving the fastest tracking speed of 96.4 FPS. Code available at https://github.com/Multi-Modality-Tracking/CKD.