YOLO-CH: A Cross-Modal Feature Interaction and Screening-Based Dual-Stream Network for UAV Small Object Detection

In the task of unmanned aerial vehicle UAV-based small object detection within complex aerial scenes, objects are characterized by significant scale variation, extremely low pixel occupancy, and dense distribution. These factors severely limit the feature representation capability and fine-grained information modeling of detectors, leading to frequent false positives and missed detections. Multi-modal image fusion, which leverages complementary information from different sensing modalities, is widely regarded as an effective approach to enhance detection performance. To improve the accuracy and robustness of object detection in aerial scenes, this paper proposes YOLO-CH, a multi-modal fusion detection method based on a dual-stream YOLOv11 architecture. The method develops parallel dual-stream feature extraction branches to encode modality-specific features from visible and infrared images. A Cross-modal Feature Transformer (CFT) module is introduced within the backbone network by step, which employs a self-attention mechanism to model intra-modal and inter-modal global dependencies, achieving deep feature interaction and enhanced representation. Furthermore, to mitigate the issue where multi-scale and small object features are susceptible to background interference, we redesigned and optimized the structure of the neck to form a high-level semantic screening feature pyramid network (High-level Screening Feature Pyramid Network, HSFPN). This module utilizes high-level semantic information in a top-down manner to refine low-level detail representations, thereby improving small object discrimination. Experimental results on the VEDAI and AVMS datasets demonstrate that the proposed method outperforms baseline models in both detection accuracy and robustness, while maintaining strong adaptability and performance across different input scales.