Contextual deconvolution network for semantic segmentation

doi:10.1016/j.patcog.2019.107152

	Contextual deconvolution network for semantic segmentation
	Fu, Jun1,2 ; Liu, Jing1 ; Li, Yong3 ; Bao, Yongjun 3; Yan, Weipeng 3; Fang, Zhiwei1,2 ; Lu, Hanqing1
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
	2020-05-01
卷号	101 页码:11
通讯作者	Liu, Jing(jliu@nlpr.ia.ac.cn)
摘要	In this paper, we propose a Contextual Deconvolution Network (CDN) and focus on context association in decoder network. Specifically, in upsampling path, we introduce two types of contextual modules to model the interdependencies of features in channel and spatial dimensions respectively. The channel contextual module captures image-level semantic information by aggregating the feature maps across spatial dimensions, and clarifies global ambiguity of features. Meanwhile, the spatial contextual module obtains patch-level semantic context by learning a spatial weight map, and enhance the feature discrimination. We embed the two contextual modules into individual components of the decoder network, thus improving the representation power and gaining more precise segment results. Thorough evaluations are performed on four challenging datasets, i.e., PASCAL VOC 2012, ADE20K, PASCAL-Context and Cityscapes dataset. Our approach achieves competitive performance with state-of-the-art models on PASCAL VOC 2012, ADE20K and Cityscapes dataset, and new state-of-the-art performance on PASCAL-Context dataset. (C) 2019 Published by Elsevier Ltd.
关键词	Semantic segmentation Deconvolution network Channel contextual module Spatial contextual module
DOI	10.1016/j.patcog.2019.107152
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61922086] ; National Natural Science Foundation of China[61872366] ; National Natural Science Foundation of China[61872364]
项目资助者	National Natural Science Foundation of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000525824600001
出版者	ELSEVIER SCI LTD
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：37[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/173211/38932
专题	紫东太初大模型研究中心_图像与视频分析
通讯作者	Liu, Jing
作者单位	1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.JD Com, Business Growth BU, Intelligent Advertising Lab, Beijing, Peoples R China
第一作者单位	模式识别国家重点实验室
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	Fu, Jun,Liu, Jing,Li, Yong,et al. Contextual deconvolution network for semantic segmentation[J]. PATTERN RECOGNITION,2020,101:11.
APA	Fu, Jun.,Liu, Jing.,Li, Yong.,Bao, Yongjun.,Yan, Weipeng.,...&Lu, Hanqing.(2020).Contextual deconvolution network for semantic segmentation.PATTERN RECOGNITION,101,11.
MLA	Fu, Jun,et al."Contextual deconvolution network for semantic segmentation".PATTERN RECOGNITION 101(2020):11.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Contextual deconvolu（3400KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载