SAR-FPN: Scale Adaptive and Reverse Fusion Object Detection

Object detection is widely used in many fields, and multi-scale feature extraction is crucial for accurate detection. The Feature Pyramid Network (FPN) is a commonly adopted feature extraction approach in object detection. Nevertheless, direct fusion between top-down feature layers in FPN leads to misalignment and loss of feature information. To address these limitations, this paper proposes a novel feature pyramid network based on FPN, termed SAR-FPN, which consists of two components: the Scale Adaptive Triple-Branch Module (SATM) and the Reverse Feature Fusion Module (RFFM). Specifically, SATM enhances the performance for large objects through its triple-branch design. It selects the appropriate branch based on object scale, assigns suitable receptive fields for objects of different sizes, and performs feature alignment. The RFFM addresses the issue of poor performance in small object detection by implementing a bottom-up feature fusion pathway. Extensive experiments on the PASCAL VOC 2012 and MS COCO 2017 datasets validated the effectiveness of SAR-FPN.