MAFTNet: Multimodal Adaptive Fusion-Based Transformer Network for Infrared and Visible Image UAV Object Detection

Infrared-visible fusion-based object detection for UAV applications aims to achieve robust all-weather surveillance by integrating complementary information from infrared and visible modalities. However, the inherent heterogeneity and dynamic quality imbalance between modalities significantly hamper effective cross-modal feature utilization. In this paper, we propose amultimodal adaptive fusion-based transformer network (MAFTNet) for effective multimodal feature learning and fusion. In the proposed model, a dual-branch modality synergy transformer (DB-MST) module is designed, which strategically recombines modal features through hybrid modality channels and transformer-based interaction, enhancing intermodal synergy. Then, a condition-driven channel reconstruction (CDCR) module is presented, which functions as a context-aware refiner, dynamically recalibrating channel contributions to highlight salient information while suppressing redundancies. Finally, a hybrid feature fusion encoder (HFFE) module is proposed, which performs hierarchical fusion and adaptive selection of multi-scale, multi-level features to generate a unified representation. Experimental results demonstrate that our proposed MAFTNet achieves superior detection accuracy and inference speed compared to state-of-the-art methods.