arXiv Is Hiring a DevOps Engineer

Work on one of the world's most important websites and make an impact on open science.

View Jobs We gratefully acknowledge support from the Simons Foundation, member institutions , and all contributors. Donate [Submitted on 9 Dec 2016 ( v1 ), last revised 19 Apr 2017 (this version, v2)]

Title: Feature Pyramid Networks for Object Detection

View PDF 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.

Submission history

From: Tsung-Yi Lin [ view email ]
[v1] Fri, 9 Dec 2016 19:55:54 UTC (518 KB)
Wed, 19 Apr 2017 22:46:32 UTC (1,874 KB)
View a PDF of the paper titled Feature Pyramid Networks for Object Detection, by Tsung-Yi Lin and 5 other authors

View PDF

TeX Source

Other Formats

Current browse context: recent | 2016-12 Change to browse by: listing | bibtex Tsung-Yi Lin
Piotr Dollár
Ross B. Girshick
Kaiming He
Bharath Hariharan export BibTeX citation

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .