Boosted MIML method for weakly-supervised image semantic segmentation

	Boosted MIML method for weakly-supervised image semantic segmentation
	Liu, Yang 1; Li, Zechao 2; Liu, Jing1 ; Lu, Hanqing1
发表期刊	MULTIMEDIA TOOLS AND APPLICATIONS
	2015
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：3[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	紫东太初大模型研究中心_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
第一作者单位	模式识别国家重点实验室
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