Consecutive Feature Network for Object Detection

Abstract

Feature Pyramid Network (FPN) is one of the best object detection algorithms in the current object detection field, which uses convolutional neural network (CNN) to detect different scaled objects in an image. However, FPN's feature fusion method ignores the influence of the consecutive feature, which hinders the information flow. In this paper, we proposed an end-to-end image detection model called CFN (Consecutive Feature Network) to overcome this problem and speed up the detection process. Under the premise of equal accuracy, the novel feature fusion method we propose can detect faster than other methods. In the feature fusion module, features from consecutive layers with different scales are merged instead of compartmental layers, which will be fed to the classification and regression subnet to predict the final detection results. On the PASCAL VOC 2007 test, without any data augmentation training skills, our proposed network can achieve 77.1 mAP (mean average precision) at the speed of 3.9 FPS (frame per second) on a single Nvidia 1080Ti GPU. Code will be made publicly available.