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

doi:10.1049/cvi2.12114

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 脑机融合与认知评估

	Contour loss for instance segmentation via k-step distance transformation image
	Guo, Xiaolong1,2 ; Lan, Xiaosong2 ; Wang, Kunfeng3 ; Li, Shuxiao1,2
发表期刊	IET COMPUTER VISION
ISSN	1751-9632
	2022-06-06
页码	11
通讯作者	Li, Shuxiao(shuxiao.li@ia.ac.cn)
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.
DOI	10.1049/cvi2.12114
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[U19B2033] ; National Natural Science Foundation of China[62076020] ; National Key RD Program[2019YFF0301801]
项目资助者	National Natural Science Foundation of China ; National Key RD Program
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000806302800001
出版者	WILEY
七大方向——子方向分类	机器人感知与决策
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/49588
专题	多模态人工智能系统全国重点实验室_脑机融合与认知评估
通讯作者	Li, Shuxiao
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 3.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
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.