CASIA OpenIR  > 飞行器智能技术
Consecutive Feature Network for Object Detection
Huang,Jiaming1,2; Lan,Xiaosong1; Li,Shuxiao1; Zhu,Chengfei1; Chang,Hongxing1
2018-08
Conference NameIEEE International Conference on Mechatronics and Automation
Conference DateAugust 5-8, 2018
Conference PlaceChangchun, China
Abstract

Feature Pyramid Network (FPN) is one of the best object detection algorithms in the current object detection field, which uses convolutional neural network (CNN) to detect different scaled objects in an image. However, FPN’s feature fusion method ignores the influence of the consecutive feature, which hinders the information flow. In this paper, we proposed an end-to-end image detection model called CFN (Consecutive Feature Network) to overcome this problem and speed up the detection process. Under the premise of equal accuracy, the novel feature fusion method we propose can detect faster than other methods. In the feature fusion module, features from consecutive layers with different scales are merged instead of compartmental layers, which will be fed to the classification and regression subnet to predict the final detection results. On the PASCAL VOC 2007 test, without any data augmentation training skills, our proposed network can achieve 77.1 mAP (mean average precision) at the speed of 3.9 FPS (frame per second) on a single Nvidia 1080Ti GPU. Code will be made publicly available.

DOI10.1109/ICMA.2018.8484571
Indexed ByEI
Language英语
Citation statistics
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23611
Collection飞行器智能技术
Corresponding AuthorHuang,Jiaming
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Huang,Jiaming,Lan,Xiaosong,Li,Shuxiao,et al. Consecutive Feature Network for Object Detection[C],2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
ICMA2018-197.pdf(991KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Huang,Jiaming]'s Articles
[Lan,Xiaosong]'s Articles
[Li,Shuxiao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Huang,Jiaming]'s Articles
[Lan,Xiaosong]'s Articles
[Li,Shuxiao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Huang,Jiaming]'s Articles
[Lan,Xiaosong]'s Articles
[Li,Shuxiao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: ICMA2018-197.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.