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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Shenglan, Yao, Rui, Zhou, Yong, Zhu, Hancheng, Sun, Kunyang, Liu, Bing, Shao, Zhiwen, Zhao, Jiaqi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910929649664000
author Li, Shenglan
Yao, Rui
Zhou, Yong
Zhu, Hancheng
Sun, Kunyang
Liu, Bing
Shao, Zhiwen
Zhao, Jiaqi
author_facet Li, Shenglan
Yao, Rui
Zhou, Yong
Zhu, Hancheng
Sun, Kunyang
Liu, Bing
Shao, Zhiwen
Zhao, Jiaqi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03507
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Modality-Guided Dynamic Graph Fusion and Temporal Diffusion for Self-Supervised RGB-T Tracking
Li, Shenglan
Yao, Rui
Zhou, Yong
Zhu, Hancheng
Sun, Kunyang
Liu, Bing
Shao, Zhiwen
Zhao, Jiaqi
Computer Vision and Pattern Recognition
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.
title Modality-Guided Dynamic Graph Fusion and Temporal Diffusion for Self-Supervised RGB-T Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.03507