Attention-Based Feature Pyramid Network for Object Detection

Abstract

Attention mechanism and feature pyramid have been widely used in various fields of deep learning in recent years. Especially, Feature Pyramid Network(FPN)becomes a popular object detection network since it is put forward in 2017, which is embedded into many well-known networks.However, FPN takes a suboptimal approach to fuse feature and detects small objects on low-level features that fused with high-level features which contain redundant information. There are very few articles discussing the way of feature fusion.So in this paper we propose a novel Attention-based Feature Pyramid Network(AFPN) which can not only enable better integration of high-level and low-level feature maps but also increase accurate semantic information of low-level features. In particular, the AFPN consists of two modules: the Feature Fusion Module(FFM) and the Feature Enhance Module(FEM). Because our model is a lightweight and general module, it is end-to-end trainable along with base CNNs. We validate our AFPN through extensive experiments on VOC and COCO detection datasets. Our experiments show consistent improvements in detection performances.