FRFDet: Efficient UAV Small Object Detection with Symmetric Sampling and Scalable Fusion
This work addresses the need for efficient, lightweight small object detection in resource-constrained UAV platforms, but the improvements are incremental over existing methods.
FRFDet introduces two plug-and-play modules (IBS and SFRCF) to improve small object detection in UAV imagery under adverse conditions, achieving state-of-the-art performance among lightweight detectors on VisDrone, UAVDT, HazyDet, and MS COCO with low computational cost and fast inference.
Small object detection in Unmanned Aerial Vehicle (UAV) imagery remains challenging under adverse conditions, including complex weather, low illumination, and sensor noise. These challenges mainly stem from severe background clutter, fine-grained detail degradation, and suboptimal semantic-spatial feature fusion, which jointly hinder robust small-object representation. To this end, we propose FRFDet, a lightweight yet effective single-stage detector tailored for UAV-based small object detection. FRFDet proposes two plug-and-play modules: Inverse Bidirectional Sampling (IBS) and Scale-Feature Relationship Cross-Fusion (SFRCF). IBS preserves critical spatial details via channel expansion-compression and bidirectional pattern reconstruction, improving feature alignment. SFRCF explicitly models scale-dependent fusion behaviors, revealing that inter-group element-wise multiplication favors compact models, while inter-group additive fusion benefits larger architectures. Extensive experiments on VisDrone, UAVDT, HazyDet, and MS COCO demonstrate that FRFDet achieves state-of-the-art performance among lightweight detectors with low computational cost, compact parameters, and fast inference, making it well suited for resource-constrained UAV platforms.