AGUnet: Annotation-guided U-net for fast one-shot video object segmentation

doi:10.1016/j.patcog.2020.107580

CASIA OpenIR > 中国科学院工业视觉智能装备工程实验室 > 精密感知与控制

	AGUnet: Annotation-guided U-net for fast one-shot video object segmentation
	Yin, Yingjie1,2,3 ; Xu, De1,3 ; Wang, Xingang1,3 ; Zhang, Lei 2
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
	2021-02-01
卷号	110 页码:10
通讯作者	Yin, Yingjie(yingjie.yin@ia.ac.cn)
摘要	The problem of semi-supervised video object segmentation has been popularly tackled by fine-tuning a general-purpose segmentation deep network on the annotated frame using hundreds of iterations of gra-dient descent. The time-consuming fine-tuning process, however, makes these methods difficult to use in practical applications. We propose a novel architecture called Annotation Guided U-net (AGUnet) for fast one-shot video object segmentation (VOS). AGUnet can quickly adapt a model trained on static images to segmenting the given target in a video by only several iterations of gradient descent. Our AGUnet is inspired by interactive image segmentation, where the interested target is segmented by using user annotated foreground. However, in AGUnet we use a fully-convolutional Siamese network to automatically annotate the foreground and background regions and fuse such annotation information into the skip connection of a U-net for VOS. Our AGUnet can be trained end-to-end effectively on static images instead of video sequences as required by many previous methods. The experiments show that AGUnet runs much faster than current state-of-the-art one-shot VOS algorithms while achieving competitive accuracy, and it has high generalization capability. (c) 2020 Elsevier Ltd. All rights reserved.
关键词	Fully-convolutional Siamese network U-net Interactive image segmentation Video object segmentation
DOI	10.1016/j.patcog.2020.107580
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61703398] ; National Natural Science Foundation of China[61672446] ; National Natural Science Foundation of China[61873266] ; Hong Kong Scholars Program[XJ2017031]
项目资助者	National Natural Science Foundation of China ; Hong Kong Scholars Program
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000585302200002
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：15[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/173211/41648
专题	中国科学院工业视觉智能装备工程实验室_精密感知与控制
通讯作者	Yin, Yingjie
作者单位	1.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing 100190, Peoples R China 2.Hong Kong Polytech Univ, Dept Comp, Hung Hom, Kowloon, Hong Kong, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
第一作者单位	精密感知与控制研究中心
通讯作者单位	精密感知与控制研究中心
推荐引用方式 GB/T 7714	Yin, Yingjie,Xu, De,Wang, Xingang,et al. AGUnet: Annotation-guided U-net for fast one-shot video object segmentation[J]. PATTERN RECOGNITION,2021,110:10.
APA	Yin, Yingjie,Xu, De,Wang, Xingang,&Zhang, Lei.(2021).AGUnet: Annotation-guided U-net for fast one-shot video object segmentation.PATTERN RECOGNITION,110,10.
MLA	Yin, Yingjie,et al."AGUnet: Annotation-guided U-net for fast one-shot video object segmentation".PATTERN RECOGNITION 110(2021):10.