SEFPN: Scale-Equalizing Feature Pyramid Network for Object Detection

Abstract

Feature Pyramid Network (FPN) is used as the neck of current popular object detection networks. Research has shown that the structure of FPN has some defects. In addition to the loss of information caused by the reduction of the channel number, the features scale of different levels are also different, and the corresponding information at different abstract levels are also different, resulting in a semantic gap between each level. We call the semantic gap level imbalance. Correlation convolution is a way to alleviate the imbalance between adjacent layers; however, how to alleviate imbalance between all levels is another problem. In this article, we propose a new simple but effective network structure called Scale-Equalizing Feature Pyramid Network (SEFPN), which generates multiple features of different scales by iteratively fusing the features of each level. SEFPN improves the overall performance of the network by balancing the semantic representation of each layer of features. The experimental results on the MS-COCO2017 dataset show that the integration of SEFPN as a standalone module into the one-stage network can further improve the performance of the detector, by ∼1AP, and improve the detection performance of Faster R-CNN, a typical two-stage network, especially for large object detection APL∼2AP.

Keywords

• object detection
• feature pyramid
• level imbalance
• correlation convolution