Boosted MIML method for weakly-supervised image semantic segmentation
Liu, Yang1; Li, Zechao2; Liu, Jing1; Lu, Hanqing1
2015
发表期刊MULTIMEDIA TOOLS AND APPLICATIONS
卷号74期号:2页码:543-559
文章类型Article
摘要Weakly-supervised image semantic segmentation aims to segment images into semantically consistent regions with only image-level labels are available, and is of great significance for fine-grained image analysis, retrieval and other possible applications. In this paper, we propose a Boosted Multi-Instance Multi-Label (BMIML) learning method to address this problem, the approach is built upon the following principles. We formulate the image semantic segmentation task as a MIML problem under the boosting framework, where the goal is to simultaneously split the superpixels obtained from over-segmented images into groups and train one classifier for each group. In the method, a loss function which uses the image-level labels as weakly-supervised constraints, is employed to suitable semantic labels to these classifiers. At the same time a contextual loss term is also combined to reduce the ambiguities existing in the training data. In each boosting round, we introduce an "objectness" measure to jointly reweigh the instances, in order to overcome the disturbance from highly frequent background superpixels. We demonstrate that BMIML outperforms the state-of-the-arts for weakly-supervised semantic segmentation on two widely used datasets, i.e., MSRC and LabelMe.
关键词Miml Weakly-supervised Semantic Segmentation Objectness
WOS标题词Science & Technology ; Technology
收录类别SCI
语种英语
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号WOS:000348445300013
引用统计
被引频次:1[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/173211/8067
专题模式识别国家重点实验室_图像与视频分析
作者单位1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing, Peoples R China
2.Nanjing Univ Sci & Technol, Sch Comp Sci, Nanjing, Jiangsu, Peoples R China
推荐引用方式
GB/T 7714
Liu, Yang,Li, Zechao,Liu, Jing,et al. Boosted MIML method for weakly-supervised image semantic segmentation[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2015,74(2):543-559.
APA Liu, Yang,Li, Zechao,Liu, Jing,&Lu, Hanqing.(2015).Boosted MIML method for weakly-supervised image semantic segmentation.MULTIMEDIA TOOLS AND APPLICATIONS,74(2),543-559.
MLA Liu, Yang,et al."Boosted MIML method for weakly-supervised image semantic segmentation".MULTIMEDIA TOOLS AND APPLICATIONS 74.2(2015):543-559.
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
Boosted MIML method (1733KB)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
[Liu, Yang]的文章
[Li, Zechao]的文章
[Liu, Jing]的文章
百度学术
百度学术中相似的文章
[Liu, Yang]的文章
[Li, Zechao]的文章
[Liu, Jing]的文章
必应学术
必应学术中相似的文章
[Liu, Yang]的文章
[Li, Zechao]的文章
[Liu, Jing]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Boosted MIML method for weakly-supervised image semantic segmentation.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。