Efficient semantic image segmentation with multi-class ranking prior

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 听觉模型与认知计算

	Efficient semantic image segmentation with multi-class ranking prior
	Pei, Deli 1,2,3,4; Li, Zhenguo 5; Ji, Rongrong 6; Sun, Fuchun 2,3,4
刊名	COMPUTER VISION AND IMAGE UNDERSTANDING
	2014-03-01
卷号	120 页码:81-90
关键词	Computer vision Machine learning Semantic segmentation Structural SVMs
英文摘要	Semantic image segmentation is of fundamental importance in a wide variety of computer vision tasks, such as scene understanding, robot navigation and image retrieval, which aims to simultaneously decompose an image into semantically consistent regions. Most of existing works addressed it as structured prediction problem by combining contextual information with low-level cues based on conditional random fields (CRFs), which are often learned by heuristic search based on maximum likelihood estimation. In this paper, we use maximum margin based structural support vector machine (S-SVM) model to combine multiple levels of cues to attenuate the ambiguity of appearance similarity and propose a novel multi-class ranking based global constraint to confine the object classes to be considered when labeling regions within an image. Compared with existing global cues, our method is more balanced between expressive power for heterogeneous regions and the efficiency of searching exponential space of possible label combinations. We then introduce inter-class co-occurrence statistics as pairwise constraints and combine them with the prediction from local and global cues based on S-SVMs framework. This enables the joint inference of labeling within an image for better consistency. We evaluate our algorithm on two challenging datasets which are widely used for semantic segmentation evaluation: MSRC-21 dataset and Stanford Background dataset and experimental results show that we obtain high competitive performance compared with state-of-the-art methods, despite that our model is much simpler and efficient. (C) 2013 Elsevier Inc. All rights reserved.
WOS标题词	Science & Technology ; Technology
类目[WOS]	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
研究领域[WOS]	Computer Science ; Engineering
关键词[WOS]	SHIFT
收录类别	SCI
语种	英语
WOS记录号	WOS:000331924500007
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/2775]
专题	数字内容技术与服务研究中心_听觉模型与认知计算
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China 3.State Key Lab Intelligent Technol & Syst, Beijing 100084, Peoples R China 4.Tsinghua Natl Lab Informat Sci & Technol, Beijing 100084, Peoples R China 5.Huawei Noahs Ark Lab, Hong Kong, Hong Kong, Peoples R China 6.Xiamen Univ, Dept Cognit Sci, Xiamen 361005, Peoples R China
推荐引用方式 GB/T 7714	Pei, Deli,Li, Zhenguo,Ji, Rongrong,et al. Efficient semantic image segmentation with multi-class ranking prior[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2014,120:81-90.
APA	Pei, Deli,Li, Zhenguo,Ji, Rongrong,&Sun, Fuchun.(2014).Efficient semantic image segmentation with multi-class ranking prior.COMPUTER VISION AND IMAGE UNDERSTANDING,120,81-90.
MLA	Pei, Deli,et al."Efficient semantic image segmentation with multi-class ranking prior".COMPUTER VISION AND IMAGE UNDERSTANDING 120(2014):81-90.