Feature Pyramid Networks for Object Detection

TL;DR

This paper introduces Feature Pyramid Networks (FPN), a novel architecture that efficiently constructs multi-scale feature maps for object detection, significantly improving accuracy while maintaining practical computational costs.

Contribution

The paper presents a top-down, lateral connection architecture for FPNs that leverages the inherent multi-scale hierarchy of deep networks, achieving state-of-the-art detection results.

Findings

FPN improves object detection accuracy on COCO benchmark.

FPN runs at 5 FPS on GPU, balancing speed and accuracy.

FPN outperforms previous single-model detectors, including 2016 challenge winners.

Abstract

Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But recent deep learning object detectors have avoided pyramid representations, in part because they are compute and memory intensive. In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. A top-down architecture with lateral connections is developed for building high-level semantic feature maps at all scales. This architecture, called a Feature Pyramid Network (FPN), shows significant improvement as a generic feature extractor in several applications. Using FPN in a basic Faster R-CNN system, our method achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles, surpassing all existing single-model entries including those from the COCO 2016 challenge winners. In addition, our method can run at 5 FPS on a GPU and thus is a practical and accurate solution to multi-scale object detection. Code will be made publicly available.