Cross Fusion RGB-T Tracking with Bi-directional Adapter

TL;DR

This paper introduces a novel RGB-T tracking architecture that effectively fuses multi-modal and temporal information using three new modules, achieving state-of-the-art results with minimal additional parameters.

Contribution

The paper presents a new cross fusion RGB-T tracking framework with three innovative modules for enhanced multi-modal and temporal information integration.

Findings

Achieves state-of-the-art performance on RGB-T tracking benchmarks.

Introduces three new modules for cross spatio-temporal information fusion.

Utilizes less than 0.3% additional modal parameters for effective fusion.

Abstract

Many state-of-the-art RGB-T trackers have achieved remarkable results through modality fusion. However, these trackers often either overlook temporal information or fail to fully utilize it, resulting in an ineffective balance between multi-modal and temporal information. To address this issue, we propose a novel Cross Fusion RGB-T Tracking architecture (CFBT) that ensures the full participation of multiple modalities in tracking while dynamically fusing temporal information. The effectiveness of CFBT relies on three newly designed cross spatio-temporal information fusion modules: Cross Spatio-Temporal Augmentation Fusion (CSTAF), Cross Spatio-Temporal Complementarity Fusion (CSTCF), and Dual-Stream Spatio-Temporal Adapter (DSTA). CSTAF employs a cross-attention mechanism to enhance the feature representation of the template comprehensively. CSTCF utilizes complementary information between different branches to enhance target features and suppress background features. DSTA adopts the adapter concept to adaptively fuse complementary information from multiple branches within the transformer layer, using the RGB modality as a medium. These ingenious fusions of multiple perspectives introduce only less than 0.3\% of the total modal parameters, but they indeed enable an efficient balance between multi-modal and temporal information. Extensive experiments on three popular RGB-T tracking benchmarks demonstrate that our method achieves new state-of-the-art performance.