TY - GEN
T1 - A new feature pyramid network for object detection
AU - Zhao, Yongqiang
AU - Han, Rui
AU - Rao, Yuan
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/9
Y1 - 2019/9
N2 - 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).
AB - 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).
KW - Accurate
KW - Fast
KW - New Feature Pyramid
UR - http://www.scopus.com/inward/record.url?scp=85077129208&partnerID=8YFLogxK
U2 - 10.1109/ICVRIS.2019.00110
DO - 10.1109/ICVRIS.2019.00110
M3 - 会议稿件
AN - SCOPUS:85077129208
T3 - Proceedings - 2019 International Conference on Virtual Reality and Intelligent Systems, ICVRIS 2019
SP - 428
EP - 431
BT - Proceedings - 2019 International Conference on Virtual Reality and Intelligent Systems, ICVRIS 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 International Conference on Virtual Reality and Intelligent Systems, ICVRIS 2019
Y2 - 14 September 2019 through 15 September 2019
ER -