This paper studies the problem of semi-supervised video object segmentation(VOS). Multiple works have shown that memory-based approaches can be effective for video object segmentation. They are mostly based on pixel-level matching, both spatially and temporally. The main shortcoming of memory-based approaches is that they do not take into account the sequential order among frames and do not exploit object-level knowledge from the target. To address this limitation, we propose to Learn position and target Consistency framework for Memory-based video object segmentation, termed as LCM. It applies the memory mechanism to retrieve pixels globally, and meanwhile learns position consistency for more reliable segmentation. The learned location response promotes a better discrimination between target and distractors. Besides, LCM introduces an object-level relationship from the target to maintain target consistency, making LCM more robust to error drifting. Experiments show that our LCM achieves state-of-the-art performance on both DAVIS and Youtube-VOS benchmark. And we rank the 1st in the DAVIS 2020 challenge semi-supervised VOS task.
翻译:本文研究了半监督视频对象分割(VOS)问题。 多个作品显示,基于记忆的方法对于视频对象分割(VOS)来说是有效的。 它们大多基于空间和时间的像素级匹配。 基于记忆的方法的主要缺点是,它们没有考虑到各框架之间的顺序顺序,也没有利用目标对象级知识。 为了解决这一限制,我们建议学习基于记忆的视频物体分割(LCM)的一致框架的位置和目标。 它运用记忆机制在全球检索像素,同时学习更可靠的分割的定位一致性。 学习的定位反应促进目标对象与转移器之间更好的区别。 此外, LCM 引入了目标对象级关系, 以保持目标一致性, 使 LCM 更强于误差漂移。 实验显示,我们的LCM 在 DAVIS 和 Youtube-VOS 基准上都取得了最先进的业绩。 我们在 DAVIS 2020 挑战半监督VOS 任务中排位第一。