Learning disentangled representation for self-supervised video object segmentation.

• This paper proposes a disentangled module to decouple the unary term and pairwise term in the one-shot video object segmentation approaches. • The pairwise term is used to capture spatio-temporal information. Meanwhile, the salient target in each frame is enhanced in the unary term. • The pairwise term tends to seek the relationship between the target pixel and its reference pixel. The unary term seeks the salience of different pixels in each frame. This paper proposes a novel self-supervised method for one-shot video object segmentation where the object annotations are only provided in the first frame. The current self-supervised video object segmentation approaches are implemented by modeling the pairwise correspondence between the target and reference frames. The pairwise correspondence only maintains spatio-temporal consistency. However, the VOS tasks not only require a spatio-temporal relationship between the two frames but also require the salient object information for each frame. In order to achieve this goal, we propose a disentangled representation strategy to disentangle the temporal correspondence into the pairwise term and unary term. The pairwise and unary terms capture inter-frame spatio-temporal and intra-frame salient object information, respectively. To demonstrate the importance of the disentangled representation, we apply the proposed approach to DAVIS-2017 and YouTube-VOS datasets. Experimental results confirm the effectiveness of the proposed solution. [ABSTRACT FROM AUTHOR]