PMVOS: Pixel-Level Matching-Based Video Object Segmentation

09/18/2020 ∙ by Suhwan Cho, et al. ∙ 1

Semi-supervised video object segmentation (VOS) aims to segment arbitrary target objects in video when the ground truth segmentation mask of the initial frame is provided. Due to this limitation of using prior knowledge about the target object, feature matching, which compares template features representing the target object with input features, is an essential step. Recently, pixel-level matching (PM), which matches every pixel in template features and input features, has been widely used for feature matching because of its high performance. However, despite its effectiveness, the information used to build the template features is limited to the initial and previous frames. We address this issue by proposing a novel method-PM-based video object segmentation (PMVOS)-that constructs strong template features containing the information of all past frames. Furthermore, we apply self-attention to the similarity maps generated from PM to capture global dependencies. On the DAVIS 2016 validation set, we achieve new state-of-the-art performance among real-time methods (> 30 fps), with a J F score of 85.6 validation sets is also impressive, with J F scores of 74.0 respectively.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

page 5

page 7

Code Repositories

PMVOS

PMVOS: Pixel-Level Matching-Based Video Object Segmentation


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.