Knowledge Commons of Institute of Automation,CAS
AGUnet: Annotation-guided U-net for fast one-shot video object segmentation | |
Yin, Yingjie1,2,3; Xu, De1,3; Wang, Xingang1,3; Zhang, Lei2 | |
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 | |
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. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论