The 2018 DAVIS Challenge on Video Object Segmentation

TL;DR

The 2018 DAVIS Challenge on Video Object Segmentation is a public competition that extends previous datasets and introduces an interactive segmentation track to advance video object segmentation methods.

Contribution

It expands the DAVIS dataset with more videos and introduces an interactive segmentation track to foster development of more robust algorithms.

Findings

Enhanced dataset with 100 additional videos and multiple objects.

Introduction of an interactive segmentation track for iterative improvement.

Benchmark results from previous editions inform current challenges.

Abstract

We present the 2018 DAVIS Challenge on Video Object Segmentation, a public competition specifically designed for the task of video object segmentation. It builds upon the DAVIS 2017 dataset, which was presented in the previous edition of the DAVIS Challenge, and added 100 videos with multiple objects per sequence to the original DAVIS 2016 dataset. Motivated by the analysis of the results of the 2017 edition, the main track of the competition will be the same than in the previous edition (segmentation given the full mask of the objects in the first frame -- semi-supervised scenario). This edition, however, also adds an interactive segmentation teaser track, where the participants will interact with a web service simulating the input of a human that provides scribbles to iteratively improve the result.