A new feature pyramid network for object detection

Yongqiang Zhao, Rui Han, Yuan Rao

科研成果: 书/报告/会议事项章节会议稿件同行评审

63 引用 (Scopus)

摘要

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).

源语言英语
主期刊名Proceedings - 2019 International Conference on Virtual Reality and Intelligent Systems, ICVRIS 2019
出版商Institute of Electrical and Electronics Engineers Inc.
428-431
页数4
ISBN(电子版)9781728150505
DOI
出版状态已出版 - 9月 2019
已对外发布
活动2019 International Conference on Virtual Reality and Intelligent Systems, ICVRIS 2019 - Jishou, 中国
期限: 14 9月 201915 9月 2019

出版系列

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

会议

会议2019 International Conference on Virtual Reality and Intelligent Systems, ICVRIS 2019
国家/地区中国
Jishou
时期14/09/1915/09/19

指纹

探究 'A new feature pyramid network for object detection' 的科研主题。它们共同构成独一无二的指纹。

引用此