Modality-Guided Dynamic Graph Fusion and Temporal Diffusion for Self-Supervised RGB-T Tracking

TL;DR

GDSTrack introduces a novel self-supervised RGB-T tracking method that dynamically fuses modalities and employs temporal diffusion to enhance robustness against noise and improve tracking accuracy.

Contribution

It proposes a dynamic graph fusion and temporal diffusion framework specifically designed for self-supervised RGB-T tracking, addressing pseudo-label noise and background interference.

Findings

Outperforms state-of-the-art on four RGB-T datasets.

Effectively reduces noise impact through dynamic graph attention.

Demonstrates robustness in challenging tracking scenarios.

Abstract

To reduce the reliance on large-scale annotations, self-supervised RGB-T tracking approaches have garnered significant attention. However, the omission of the object region by erroneous pseudo-label or the introduction of background noise affects the efficiency of modality fusion, while pseudo-label noise triggered by similar object noise can further affect the tracking performance. In this paper, we propose GDSTrack, a novel approach that introduces dynamic graph fusion and temporal diffusion to address the above challenges in self-supervised RGB-T tracking. GDSTrack dynamically fuses the modalities of neighboring frames, treats them as distractor noise, and leverages the denoising capability of a generative model. Specifically, by constructing an adjacency matrix via an Adjacency Matrix Generator (AMG), the proposed Modality-guided Dynamic Graph Fusion (MDGF) module uses a dynamic adjacency matrix to guide graph attention, focusing on and fusing the object's coherent regions. Temporal Graph-Informed Diffusion (TGID) models MDGF features from neighboring frames as interference, and thus improving robustness against similar-object noise. Extensive experiments conducted on four public RGB-T tracking datasets demonstrate that GDSTrack outperforms the existing state-of-the-art methods. The source code is available at https://github.com/LiShenglana/GDSTrack.