Meta learning with differentiable closed-form solver for fast video object segmentation

Yu Liu, Lingqiao Liu, Haokui Zhang, Hamid Rezatofighi, Qingsen Yan, Ian Reid

科研成果: 书/报告/会议事项章节会议稿件同行评审

7 引用 (Scopus)

摘要

Video object segmentation plays a vital role to many robotic tasks, beyond the satisfied accuracy, quickly adapt to the new scenario with very limited annotations and conduct a quick inference are also important. In this paper, we are specifically concerned with the task of fast segmenting all pixels of a target object in all frames, given the annotation mask in the first frame. Even when such annotation is available, this remains a challenging problem because of the changing appearance and shape of the object over time. In this paper, we tackle this task by formulating it as a meta-learning problem, where the base learner grasping the semantic scene understanding for a general type of objects, and the meta learner quickly adapting the appearance of the target object with a few examples. Our proposed meta-learning method uses a closed form optimizer, the so-called "ridge regression", which has been shown to be conducive for fast and better training convergence. Moreover, we propose a mechanism, named "block splitting", to further speed up the training process as well as to reduce the number of learning parameters. In comparison with the state-of-the art methods, our proposed framework achieves significant boost up in processing speed, while having highly comparable performance compared to the best performing methods on the widely used datasets. Video demo can be found here 1.

源语言英语
主期刊名2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
出版商Institute of Electrical and Electronics Engineers Inc.
8439-8446
页数8
ISBN(电子版)9781728162126
DOI
出版状态已出版 - 24 10月 2020
已对外发布
活动2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020 - Las Vegas, 美国
期限: 24 10月 202024 1月 2021

出版系列

姓名IEEE International Conference on Intelligent Robots and Systems
ISSN(印刷版)2153-0858
ISSN(电子版)2153-0866

会议

会议2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
国家/地区美国
Las Vegas
时期24/10/2024/01/21

指纹

探究 'Meta learning with differentiable closed-form solver for fast video object segmentation' 的科研主题。它们共同构成独一无二的指纹。

引用此