Boosted MIML method for weakly-supervised image semantic segmentation
文献类型：期刊论文
| 作者 | Liu, Yang1; Li, Zechao2; Liu, Jing1 ; Lu, Hanqing1
|
| 刊名 | MULTIMEDIA TOOLS AND APPLICATIONS
 |
| 出版日期 | 2015 |
| 卷号 | 74期号:2页码:543-559 |
| 关键词 | MIML Weakly-supervised Semantic segmentation Objectness |
| 英文摘要 | 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. |
| WOS标题词 | Science & Technology ; Technology |
| 类目[WOS] | Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
| 研究领域[WOS] | Computer Science ; Engineering |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000348445300013 |
| 公开日期 | 2015-09-22 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/8067]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
| 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. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。