About this scholarly article

Feature Pyramid Networks for Object Detection by Tsung-Yi Lin; Piotr Dollar; Ross Girshick; Kaiming He; Bharath Hariharan; Serge Belongie is a scholarly article available to read on EtoBox.

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 topdown 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 singlemodel 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.

Author

Tsung-Yi Lin; Piotr Dollar; Ross Girshick; Kaiming He; Bharath Hariharan; Serge Belongie

Publisher

IEEE

Published

2017

Language

EN