版权说明 操作指南
首页 > 成果 > 详情

MULTI-TASK FEATURE SELECTION FOR ADVANCING PERFORMANCE OF IMAGE SEGMENTATION

认领
导出
反馈
分享
QQ微信 微博
成果类型:
会议论文
作者:
Liu, Han;Zhao, Huihuang*
通讯作者:
Zhao, Huihuang
作者机构:
[Liu, Han] Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF24 3AA, Wales.
[Zhao, Huihuang] Hengyang Normal Univ, Coll Comp Sci & technol, Hengyang 421008, Peoples R China.
通讯机构:
[Zhao, Huihuang] H
Hengyang Normal Univ, Coll Comp Sci & technol, Hengyang 421008, Peoples R China.
语种:
英文
关键词:
Machine learning;Multi-task learning;Multi-task feature selection;Image segmentation
期刊:
PROCEEDINGS OF 2018 INTERNATIONAL CONFERENCE ON WAVELET ANALYSIS AND PATTERN RECOGNITION (ICWAPR)
年:
2018
页码:
244-249
会议名称:
International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)
会议论文集名称:
International Conference on Wavelet Analysis and Pattern Recognition
会议时间:
JUL 15-18, 2018
会议地点:
Chengdu, PEOPLES R CHINA
会议主办单位:
[Liu, Han] Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF24 3AA, Wales.^[Zhao, Huihuang] Hengyang Normal Univ, Coll Comp Sci & technol, Hengyang 421008, Peoples R China.
会议赞助商:
Diee, Univ Alberta, Ulster Univ, IEEE, Portsmouth Univ, Univ Hyogo, IEEE Syst Man & Cybernet Soc, Univ Adelaide, Chengdu Univ, Univ Cagliari, Dept Elect & Electr Engn, Natl Key Lab Sci & Technol Blind Signal Proc
出版地:
345 E 47TH ST, NEW YORK, NY 10017 USA
出版者:
IEEE
ISBN:
978-1-5386-5218-3
基金类别:
National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61503128]; Science and Technology Plan Project of Hunan Province [2016TP102]; Scientific Research Fund of Hunan Provincial Education DepartmentHunan Provincial Education Department [14B025, 16C0311]; Hunan Provincial Natural Science Fundationtion [2017JJ4001]
机构署名:
本校为通讯机构
院系归属:
计算机科学与技术学院
摘要:
Image segmentation is a popular application area of machine learning. In this context, each target region drawn from an image is defined as a class towards recognition of instances that belong to this region (class). In order to train classifiers that recognize the target region to which an instance belongs, it is important to extract and select features relevant to the region. In traditional machine learning, all features extracted from different regions are simply used together to form a single feature set for training classifiers, and feature selection is usually designed to evaluate the ca...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com