CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Boosted MIML method for weakly-supervised image semantic segmentation
Liu, Yang1; Li, Zechao2; Liu, Jing1; Lu, Hanqing1
Source PublicationMULTIMEDIA TOOLS AND APPLICATIONS
2015
Volume74Issue:2Pages:543-559
SubtypeArticle
AbstractWeakly-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.
KeywordMiml Weakly-supervised Semantic Segmentation Objectness
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000348445300013
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/8067
Collection模式识别国家重点实验室_图像与视频分析
Affiliation1.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
Recommended Citation
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.
Files in This Item: Download All
File Name/Size DocType Version Access License
Boosted MIML method (1733KB)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
[Liu, Yang]'s Articles
[Li, Zechao]'s Articles
[Liu, Jing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu, Yang]'s Articles
[Li, Zechao]'s Articles
[Liu, Jing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu, Yang]'s Articles
[Li, Zechao]'s Articles
[Liu, Jing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Boosted MIML method for weakly-supervised image semantic segmentation.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

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