Context propagation embedding network for weakly supervised semantic segmentation

doi:10.1007/s11042-020-08787-9

	Context propagation embedding network for weakly supervised semantic segmentation
	Xu, Yajun 1; Mao, Zhendong 2; Chen, Zhineng3 ; Wen, Xin 1; Li, Yangyang 4
发表期刊	MULTIMEDIA TOOLS AND APPLICATIONS
ISSN	1380-7501
	2020-03-30
页码	18
通讯作者	Mao, Zhendong(maozhendong2008@gmail.com)
摘要	Weakly-supervised semantic segmentation with image-level labels has much significance as it facilitates related practical applications under lightweight manual annotations. Recent researches first infer the visual cues, referred as discriminative regions corresponding to each object category on images using deep convolutional classification networks. Then they expand visual cues to generate initial segmentation masks. Despite the remarkable progress, the segmentation performance still remains unsatisfactory due to the absence of complete visual cues. Using these low-quality visual cues as prior will have the limitation on improving segmentation performance. To overcome this problem, we propose a novel context propagation embedding network, i.e., the CPENet to generate high-quality visual cues, which focuses on learning semantic relationship between each region and its surrounding neighbors and selectively propagates discriminative information to non-discriminative, object related regions. Our methods can provide reliable initial segmentation masks for training subsequent segmentation network to generate final segmentation results. In addition, we refined convolutional block attention module (CBAM) [30] to hierarchically extract more category-aware features by capturing global context related information and further promote the propagation process. Experiments on benchmark demonstrate that our proposed method obtains superior performance over the state-of-the-arts.
关键词	Weakly supervised Semantic segmentation Context propagation High-quality visual cues
DOI	10.1007/s11042-020-08787-9
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China
项目资助者	National Natural Science Foundation of China
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:000522592200005
出版者	SPRINGER
七大方向——子方向分类	图像视频处理与分析
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/173211/38759
专题	数字内容技术与服务研究中心_远程智能医疗
通讯作者	Mao, Zhendong
作者单位	1.Chinese Acad Sci, Inst Informat Engn, Sch Cyber Secur, Beijing, Peoples R China 2.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 4.China Acad Elect & Informat Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Xu, Yajun,Mao, Zhendong,Chen, Zhineng,et al. Context propagation embedding network for weakly supervised semantic segmentation[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2020:18.
APA	Xu, Yajun,Mao, Zhendong,Chen, Zhineng,Wen, Xin,&Li, Yangyang.(2020).Context propagation embedding network for weakly supervised semantic segmentation.MULTIMEDIA TOOLS AND APPLICATIONS,18.
MLA	Xu, Yajun,et al."Context propagation embedding network for weakly supervised semantic segmentation".MULTIMEDIA TOOLS AND APPLICATIONS (2020):18.