CASIA OpenIR  > 脑网络组研究中心
Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection
Zhang Jinpeng1,2,3,4; Zhang Jinming5; Yu, Shan1,2,3,4
Source PublicationSENSORS
ISSN1424-8220
2018-10-01
Volume18Issue:10Pages:19
Abstract

In the image object detection task, a huge number of candidate boxes are generated to match with a relatively very small amount of ground-truth boxes, and through this method the learning samples can be created. But in fact the vast majority of the candidate boxes do not contain valid object instances and should be recognized and rejected during the training and evaluation of the network. This leads to extra high computation burden and a serious imbalance problem between object and none-object samples, thereby impeding the algorithm's performance. Here we propose a new heuristic sampling method to generate candidate boxes for two-stage detection algorithms. It is generally applicable to the current two-stage detection algorithms to improve their detection performance. Experiments on COCO dataset showed that, relative to the baseline model, this new method could significantly increase the detection accuracy and efficiency.

Keywordimage object detection RCNN Faster RCNN Light Head RCNN
DOI10.3390/s18103415
WOS KeywordFEATURES
Indexed BySCI
Language英语
Funding ProjectNational Key Research and Development Program of China[2017YFA0105203] ; Strategic Priority Research Program of the Chinese Academy of Sciences (CAS)[XDBS01040200] ; Hundred-Talent Program of CAS
WOS Research AreaChemistry ; Electrochemistry ; Instruments & Instrumentation
WOS SubjectChemistry, Analytical ; Electrochemistry ; Instruments & Instrumentation
WOS IDWOS:000448661500243
PublisherMDPI
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/22561
Collection脑网络组研究中心
Corresponding AuthorZhang Jinpeng
Affiliation1.Chinese Acad Sci, Brainnetome Ctr, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
5.Xi An Jiao Tong Univ, State Key Lab Mfg Syst Engn, Xian 710049, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhang Jinpeng,Zhang Jinming,Yu, Shan. Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection[J]. SENSORS,2018,18(10):19.
APA Zhang Jinpeng,Zhang Jinming,&Yu, Shan.(2018).Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection.SENSORS,18(10),19.
MLA Zhang Jinpeng,et al."Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection".SENSORS 18.10(2018):19.
Files in This Item: Download All
File Name/Size DocType Version Access License
Hot Anchors_ A Heuri(2702KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang Jinpeng]'s Articles
[Zhang Jinming]'s Articles
[Yu, Shan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang Jinpeng]'s Articles
[Zhang Jinming]'s Articles
[Yu, Shan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang Jinpeng]'s Articles
[Zhang Jinming]'s Articles
[Yu, Shan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Hot Anchors_ A Heuristic Anchors Sampling Method in RCNN-Based Object Detection.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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