Contour loss for instance segmentation via k-step distance transformation image

doi:10.1049/cvi2.12114

CORC > 自动化研究所 > 中国科学院自动化研究所 > 综合信息系统研究中心 > 脑机融合与认知评估

	Contour loss for instance segmentation via k-step distance transformation image
	Guo, Xiaolong 2,3; Lan, Xiaosong 2; Wang, Kunfeng 1; Li, Shuxiao 2,3
刊名	IET COMPUTER VISION
	2022-06-06
页码	11
ISSN号	1751-9632
DOI	10.1049/cvi2.12114
通讯作者	Li, Shuxiao(shuxiao.li@ia.ac.cn)
英文摘要	Instance segmentation aims to locate targets in the image and segment each target at the pixel level, which is one of the most important tasks in computer vision. Mask R-CNN is a classic method of instance segmentation, but we find that its predicted masks are unclear and inaccurate near contours. To cope with this problem, we draw on the idea of contour matching based on distance transformation image and propose a novel loss function called contour loss. Contour loss is designed to specifically optimise the contour parts of the predicted masks, thus can assure more accurate instance segmentation. To make the proposed contour loss be jointly trained under modern neural network frameworks, we design a differentiable k-step distance transformation image calculation module, which can approximately compute truncated distance transformation images of the predicted mask and the corresponding ground-truth mask online. The proposed contour loss can be integrated into existing instance segmentation methods such as Mask R-CNN, and combined with their original loss functions without modification of the structures of inference network, thus has strong versatility. Experimental results on COCO show that contour loss is effective, which can further improve instance segmentation performances.
资助项目	National Natural Science Foundation of China[U19B2033] ; National Natural Science Foundation of China[62076020] ; National Key RD Program[2019YFF0301801]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	WILEY
WOS记录号	WOS:000806302800001
资助机构	National Natural Science Foundation of China ; National Key RD Program
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/49587]
专题	综合信息系统研究中心_脑机融合与认知评估
通讯作者	Li, Shuxiao
作者单位	1.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Guo, Xiaolong,Lan, Xiaosong,Wang, Kunfeng,et al. Contour loss for instance segmentation via k-step distance transformation image[J]. IET COMPUTER VISION,2022:11.
APA	Guo, Xiaolong,Lan, Xiaosong,Wang, Kunfeng,&Li, Shuxiao.(2022).Contour loss for instance segmentation via k-step distance transformation image.IET COMPUTER VISION,11.
MLA	Guo, Xiaolong,et al."Contour loss for instance segmentation via k-step distance transformation image".IET COMPUTER VISION (2022):11.