Feature Pyramid Networks for Object Detection
This provides a practical and accurate solution for multi-scale object detection in computer vision, addressing a known bottleneck in deep learning detectors.
The paper tackled the problem of multi-scale object detection by introducing Feature Pyramid Networks (FPN), which construct feature pyramids efficiently from deep convolutional networks, achieving state-of-the-art results on the COCO benchmark with a single model and running at 5 FPS on a GPU.
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.