arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.03234cs.CV
收藏

运动监督的共部分分割

Motion-supervised Co-Part Segmentation

University of Trento(特伦托大学);Télécom Paris, Institut polytechnique de Paris(巴黎理工学院巴黎电信学院);Snap Inc.(Snap公司);Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会);Huawei Technologies Ireland(华为爱尔兰技术公司)

Aliaksandr Siarohin, Subhankar Roy, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, Nicu Sebe

摘要:

最近的共同部分分割方法大多在监督学习环境中操作,这需要大量的注释数据用于训练。为了克服这一限制,我们提出了一种自监督的深度学习方法来进行共部分分割。与以前的作品不同,我们的方法发展了这样一种想法,即可以利用从视频中推断出的运动信息来发现有意义的对象部分。为此,我们的方法依赖于从同一视频中采样的成对帧。该网络学习预测部分片段以及两帧之间的运动表示,这允许重建目标图像。通过对公开视频序列进行广泛的实验评估,我们证明了我们的方法可以产生改进的分割图,相对于以前的自监督共部分分割方法。

英文摘要:

Recent co-part segmentation methods mostly operate in a supervised learning setting, which requires a large amount of annotated data for training. To overcome this limitation, we propose a self-supervised deep learning method for co-part segmentation. Differently from previous works, our approach develops the idea that motion information inferred from videos can be leveraged to discover meaningful object parts. To this end, our method relies on pairs of frames sampled from the same video. The network learns to predict part segments together with a representation of the motion between two frames, which permits reconstruction of the target image. Through extensive experimental evaluation on publicly available video sequences we demonstrate that our approach can produce improved segmentation maps with respect to previous self-supervised co-part segmentation approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑