RS-YOLOX: A High-Precision Detector for Object Detection in Satellite Remote Sensing Images
To address critical challenges in satellite remote sensing imagery—namely, low detection accuracy, poor small-object recognition, and severe foreground-background class imbalance—this paper proposes RS-YOLOX. Methodologically, it integrates the ECA (Efficient Channel Attention) mechanism into the YOLOX backbone to enhance channel-wise feature responsiveness; adopts Adaptive Spatial Feature Fusion (ASFF) for adaptive multi-scale feature aggregation; employs Varifocal Loss to mitigate class imbalance and improve hard-example learning; and incorporates Slice-Assisted Hyper-Inference (SAHI) to boost small-object recall. Evaluated on three benchmark remote sensing datasets—DOTA-v1.5, TGRS-HRRSD, and RSOD—RS-YOLOX achieves state-of-the-art (SOTA) performance across all, with particularly notable gains in small-object detection and dense-scene scenarios. These results validate both the effectiveness and generalizability of the proposed framework.