CASIA OpenIR  > 脑网络组研究
Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection
Zhang Jinpeng1,2,3,4; Zhang Jinming5; Yu, Shan1,2,3,4
发表期刊SENSORS
ISSN1424-8220
2018-10-01
卷号18期号:10页码:19
摘要

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.

关键词image object detection RCNN Faster RCNN Light Head RCNN
DOI10.3390/s18103415
关键词[WOS]FEATURES
收录类别SCI
语种英语
资助项目Hundred-Talent Program of CAS ; Strategic Priority Research Program of the Chinese Academy of Sciences (CAS)[XDBS01040200] ; National Key Research and Development Program of China[2017YFA0105203] ; National 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研究方向Chemistry ; Electrochemistry ; Instruments & Instrumentation
WOS类目Chemistry, Analytical ; Electrochemistry ; Instruments & Instrumentation
WOS记录号WOS:000448661500243
出版者MDPI
引用统计
被引频次:6[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/22561
专题脑网络组研究
通讯作者Zhang Jinpeng
作者单位1.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
第一作者单位模式识别国家重点实验室
通讯作者单位模式识别国家重点实验室
推荐引用方式
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.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Hot Anchors_ A Heuri(2702KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang Jinpeng]的文章
[Zhang Jinming]的文章
[Yu, Shan]的文章
百度学术
百度学术中相似的文章
[Zhang Jinpeng]的文章
[Zhang Jinming]的文章
[Yu, Shan]的文章
必应学术
必应学术中相似的文章
[Zhang Jinpeng]的文章
[Zhang Jinming]的文章
[Yu, Shan]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Hot Anchors_ A Heuristic Anchors Sampling Method in RCNN-Based Object Detection.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。