Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
6-2021
Abstract
This paper tackles the task of Few-Shot Video Object Segmentation (FSVOS), i.e., segmenting objects in the query videos with certain class specified in a few labeled support images. The key is to model the relationship between the query videos and the support images for propagating the object information. This is a many-to-many problem and often relies on full-rank attention, which is computationally intensive. In this paper, we propose a novel Domain Agent Network (DAN), breaking down the full-rank attention into two smaller ones. We consider one single frame of the query video as the domain agent, bridging between the support images and the query video. Our DAN allows a linear space and time complexity as opposed to the original quadratic form with no loss of performance. In addition, we introduce a learning strategy by combining meta-learning with online learning to further improve the segmentation accuracy. We build a FSVOS benchmark on the Youtube-VIS dataset and conduct experiments to demonstrate that our method outperforms baselines on both computational cost and accuracy, achieving the state-of-the-art performance
Keywords
Agent network; Breakings; Linear spaces; Linear time; Many to many; Novel domain; Object information; Query video; Single frames; Video objects segmentations
Discipline
Graphics and Human Computer Interfaces | Numerical Analysis and Scientific Computing
Research Areas
Information Systems and Management
Publication
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Virtual, June 19-25
Last Page
14035
ISBN
9781665445092
Identifier
10.1109/CVPR46437.2021.01382
Publisher
IEEE
City or Country
New Jersey, USA
Citation
CHEN, Haoxin; WU, Hanjie; ZHAO, Nanxuan; REN, Sucheng; and HE, Shengfeng.
Delving deep into many-to-many attention for few-shot video object segmentation. (2021). Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Virtual, June 19-25. 14035.
Available at: https://ink.library.smu.edu.sg/sis_research/8527
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Included in
Graphics and Human Computer Interfaces Commons, Numerical Analysis and Scientific Computing Commons