AGSFCOS: Based on attention mechanism and Scale-Equalizing pyramid network of object detection
This work incrementally improves object detection accuracy for computer vision applications, focusing on anchor-free models.
The authors tackled improving anchor-free object detection by addressing feature extraction and feature pyramid network utilization, resulting in a model that achieves 39.5% COCO AP with ResNet50, showing accuracy improvements over popular models like YOLOv3 and FCOS.
Recently, the anchor-free object detection model has shown great potential for accuracy and speed to exceed anchor-based object detection. Therefore, two issues are mainly studied in this article: (1) How to let the backbone network in the anchor-free object detection model learn feature extraction? (2) How to make better use of the feature pyramid network? In order to solve the above problems, Experiments show that our model has a certain improvement in accuracy compared with the current popular detection models on the COCO dataset, the designed attention mechanism module can capture contextual information well, improve detection accuracy, and use sepc network to help balance abstract and detailed information, and reduce the problem of semantic gap in the feature pyramid network. Whether it is anchor-based network model YOLOv3, Faster RCNN, or anchor-free network model Foveabox, FSAF, FCOS. Our optimal model can get 39.5% COCO AP under the background of ResNet50.