Receptive-Field Fusion and Cross-Scale Global Modeling for Infrared and Visible Small Object Detection

Small-object detection in unmanned aerial vehicle (UAV)-based visible and infrared imagery remains a challenge because of scale variations, weak thermal signals, and complex background interference. This paper proposes a dual-modality detection model that integrates receptive field enhancement and global cross-scale semantic fusion, built upon the YOLOv11 architecture. A reparameterized receptive-field attention convolution(RFAConv) module expands shallow-layer receptive fields via a dual-branch structure to improve spatial sensitivity and modality adaptability. A transformer-guided global fusion mechanism aligns multiscale semantics nonlocally, and a mixed local channel attention module enhanced focus on small-object regions while suppressing noise. Experiments on the VisDrone2021 and HIT-UAV datasets show that the proposed method achieves superior accuracy, structural efficiency, and robustness compared with existing lightweight and transformer-based detectors.