TY - GEN
T1 - Meta learning with differentiable closed-form solver for fast video object segmentation
AU - Liu, Yu
AU - Liu, Lingqiao
AU - Zhang, Haokui
AU - Rezatofighi, Hamid
AU - Yan, Qingsen
AU - Reid, Ian
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/24
Y1 - 2020/10/24
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85102408163&partnerID=8YFLogxK
U2 - 10.1109/IROS45743.2020.9341282
DO - 10.1109/IROS45743.2020.9341282
M3 - 会议稿件
AN - SCOPUS:85102408163
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 8439
EP - 8446
BT - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2020
Y2 - 24 October 2020 through 24 January 2021
ER -