Learning Position and Target Consistency for Memory-based Video Object Segmentation

TL;DR

This paper introduces LCM, a novel memory-based video object segmentation framework that incorporates position and target consistency to improve segmentation accuracy and robustness, achieving state-of-the-art results.

Contribution

The paper proposes a new approach that learns position and target consistency in memory-based VOS, addressing limitations of previous pixel-level matching methods.

Findings

Achieves state-of-the-art performance on DAVIS and Youtube-VOS benchmarks.

Ranks 1st in the DAVIS 2020 semi-supervised VOS challenge.

Demonstrates improved robustness to error drifting.

Abstract

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.