A new feature pyramid network for object detection

Yongqiang Zhao, Rui Han, Yuan Rao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

63 Scopus citations

Abstract

Aiming at the problems of high computational cost based on deep backbones (e.g., ResNet-50, ResNet-101, DenseNet-169) in the state-of-the-art method about object detector, this paper improves the capability of feature representations by using New Feature Pyramid module on the basis of fast lightweight backbone network (vgg-16), and finally establishes a fast and accurate detector. The architecture of our model is named New FPN (New Feature Pyramid Network). Based on the structure of Feature Pyramid Network, we design a novel New Feature Pyramid Network, which consists of a combination of top-down and bottom-up connections to fuse features across scales, and achieves high-level semantic feature map at all scales. The experimental results show that New FPN achieves state-of-the-art detection accuracy (i.e. 79.2%mAP) on PASCAL VOC 2007 with high efficiency (i.e. 73FPS).

Original languageEnglish
Title of host publicationProceedings - 2019 International Conference on Virtual Reality and Intelligent Systems, ICVRIS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages428-431
Number of pages4
ISBN (Electronic)9781728150505
DOIs
StatePublished - Sep 2019
Externally publishedYes
Event2019 International Conference on Virtual Reality and Intelligent Systems, ICVRIS 2019 - Jishou, China
Duration: 14 Sep 201915 Sep 2019

Publication series

NameProceedings - 2019 International Conference on Virtual Reality and Intelligent Systems, ICVRIS 2019

Conference

Conference2019 International Conference on Virtual Reality and Intelligent Systems, ICVRIS 2019
Country/TerritoryChina
CityJishou
Period14/09/1915/09/19

Keywords

  • Accurate
  • Fast
  • New Feature Pyramid

Fingerprint

Dive into the research topics of 'A new feature pyramid network for object detection'. Together they form a unique fingerprint.

Cite this