RetinaGate: A Gated Feature Pyramid Network for Improved Object Detection with SE-based Attention

Object detection is a critical task in computer vision with wide-ranging applications, from autonomous driving to surveillance systems. Despite notable progress, challenges such as detecting small objects, managing occlusions, and effectively integrating multiscale features persist. We propose RetinaGate, a novel object detection architecture that introduces a Gated Feature Pyramid Network (G-FPN) to adaptively fuse multi-scale features, enhanced by Squeeze-and-Excitation-based channel attention for improved accuracy. As a plot-and-play model, G-FPN can be seamlessly integrated into existing detection models to enhance their accuracy. These enhancements strengthen the model's capacity to capture fine-grained details and leverage contextual information more effectively. Experimental results on three benchmark datasets demonstrate the RetinaGate outperforms the baseline RetinaNet in terms of detection accuracy, particularly in challenging detection scenarios such as underwater.