Super-resolution semantic segmentation with relation calibrating network

doi:10.1016/j.patcog.2021.108501

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 图像与视频分析团队

	Super-resolution semantic segmentation with relation calibrating network
	Jiang, Jie 1,2; Liu, Jing 1,2; Fu, Jun 2; Wang, Weining 1,2; Lu, Hanqing 1,2
刊名	PATTERN RECOGNITION
	2022-04-01
卷号	124 页码:10
关键词	Image semantic segmentation Super-resolution semantic segmentation Relation calibrating
ISSN号	0031-3203
DOI	10.1016/j.patcog.2021.108501
通讯作者	Liu, Jing(jliu@nlpr.ia.ac.cn)
英文摘要	To achieve high-resolution segmentation results, typical semantic segmentation models often require high-resolution inputs. However, high-resolution inputs inevitably bring high cost on computation, which limits its application seriously in realistic scenarios. To address the problem, we propose to predict a high-resolution semantic segmentation result with a degraded low-resolution image as input, which is called super-resolution semantic segmentation in this paper. We further propose a Relation Calibrating Network (RCNet) for this task. Specifically, we propose two modules, namely Relation Upsampling Module (RUM) and Feature Calibrating Module (FCM). In RUM, the input feature map generates the relation map of pixels in low-resolution, which is then gradually upsampled to high-resolution. Meanwhile, FCM takes the input feature map and the relation map from RUM as inputs, gradually calibrating the feature. Finally, the last FCM outputs the high-resolution segmentation results. We conduct extensive experiments to verify the effectiveness of our method. Specially, we achieve a comparable segmentation result (from 70.01% to 70.90%) with only 1/4 of the computational cost (from 1107.57 to 255.72 GFLOPs) based on FCN on Cityscapes dataset. (c) 2021 Elsevier Ltd. All rights reserved.
资助项目	National Natural Science Foundation of China[61922086] ; National Natural Science Foundation of China[61872366] ; Beijing Natural Science Foundation[4192059] ; Beijing Natural Science Foundation[JQ20022]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000740812500002
资助机构	National Natural Science Foundation of China ; Beijing Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/47178]
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
通讯作者	Liu, Jing
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Jiang, Jie,Liu, Jing,Fu, Jun,et al. Super-resolution semantic segmentation with relation calibrating network[J]. PATTERN RECOGNITION,2022,124:10.
APA	Jiang, Jie,Liu, Jing,Fu, Jun,Wang, Weining,&Lu, Hanqing.(2022).Super-resolution semantic segmentation with relation calibrating network.PATTERN RECOGNITION,124,10.
MLA	Jiang, Jie,et al."Super-resolution semantic segmentation with relation calibrating network".PATTERN RECOGNITION 124(2022):10.