Enhanced SSD with interactive multi-scale attention features for object detection

Single Shot MultiBox Detector (SSD) method using multi-scale feature maps for object detection, showing outstanding performance in object detection task. However, as a one-stage detection method, it's difficult for SSD methods to quickly notice significant areas of objects in the image. In the SSD network structure, feature maps of different scales are used to independently predict object, and there is a lack of interaction between low-level feature maps and high-level feature maps. In this paper we propose an enhanced SSD method using interactive multi-scale attention features (MA-SSD). Our method uses the attention mechanism to generate attention features of multiple scales and adds it to the original detection branch of the SSD method, which effectively enhances the feature representation ability and improves the detection accuracy. At the same time, the feature of different detection scales interacts with each other, and all the detection branches in our method have a parallel structure, which ensures the detection efficiency. Our proposed method achieves competitive performance on the public dataset PascalVOC.

Automated summary

The Single Shot MultiBox Detector(SSD) uses multi-scale feature maps for object detection and has outstanding performance. However, as a one-stage detection method, SSD struggles to quickly identify significant areas of objects. Our proposed enhanced SSD method, MA-SSD, utilizes interactive multi-scale attention features to improve feature representation and detection accuracy, while ensuring detection efficiency through a parallel structure. This method achieves competitive performance on the public dataset PascalVOC.