Multi-scale spatial context-based semantic edge detection

doi:10.1016/j.inffus.2020.08.014

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 三维可视计算

	Multi-scale spatial context-based semantic edge detection
	Ma, Wei 1; Gong, Chaofan 1; Xu, Shibiao2 ; Zhang, Xiaopeng2
发表期刊	INFORMATION FUSION
ISSN	1566-2535
	2020-12-01
卷号	64 页码:238-251
通讯作者	Xu, Shibiao(shibiao.xu@nlpr.ia.ac.cn)
摘要	The good fusion of multi-scale features obtained by Convolutional neural networks (CNNs) is key to semantic edge detection; however, obtaining fusion is challenging. This paper presents a Multi-scale Spatial Context-based deep network for Semantic Edge Detection (MSC-SED). Different from state-of-the-art methods, MSC-SED gradually fuses multi-scale low-to-high level CNN features in an end-to-end architecture. This fusion structure obtains rich multi-scale features while enhancing the details of higher-level features. Beside the overall structure, we present the following two functional modules: the Context Aggregation Module (CAM) and Location-Aware fusion Module (LAM). The CAM helps to enrich context in features at each stage, before and after fusion. The LAM helps to selectively integrate lower-level features. The proposed method outperforms state-of-the-art approaches in terms of both the edge quality and the accuracy of edge categorization on both the SBD and Cityscapes datasets.
关键词	Semantic edge detection Convolutional neural network Multi-scale feature fusion Location-aware information fusion Gradual fusion
DOI	10.1016/j.inffus.2020.08.014
关键词[WOS]	IMAGE ; BOUNDARIES
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61771026] ; National Natural Science Foundation of China[61620106003] ; National Natural Science Foundation of China[91860124] ; National Natural Science Foundation of China[61971418] ; National Natural Science Foundation of China[61972459] ; National Key Research and Development Program of China[2018YFB2100602] ; Key Project of Beijing Municipal Education Commission, China[KZ201910005008]
项目资助者	National Natural Science Foundation of China ; National Key Research and Development Program of China ; Key Project of Beijing Municipal Education Commission, China
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods
WOS记录号	WOS:000572143400001
出版者	ELSEVIER
七大方向——子方向分类	模式识别基础
引用统计	被引频次：19[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/173211/41996
专题	多模态人工智能系统全国重点实验室_三维可视计算
通讯作者	Xu, Shibiao
作者单位	1.Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Ma, Wei,Gong, Chaofan,Xu, Shibiao,et al. Multi-scale spatial context-based semantic edge detection[J]. INFORMATION FUSION,2020,64:238-251.
APA	Ma, Wei,Gong, Chaofan,Xu, Shibiao,&Zhang, Xiaopeng.(2020).Multi-scale spatial context-based semantic edge detection.INFORMATION FUSION,64,238-251.
MLA	Ma, Wei,et al."Multi-scale spatial context-based semantic edge detection".INFORMATION FUSION 64(2020):238-251.