The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation

TL;DR

The 2019 DAVIS Challenge introduces an unsupervised multi-object video segmentation track, encouraging development of algorithms that generate object proposals and track them across frames without human supervision, advancing the field of VOS.

Contribution

This paper presents the first unsupervised multi-object segmentation track in the DAVIS Challenge, including dataset re-annotations, rules, and evaluation metrics for the new task.

Findings

New unsupervised track with non-overlapping object proposals

Re-annotated DAVIS 2017 datasets for unsupervised segmentation

Established evaluation metrics for unsupervised VOS

Abstract

We present the 2019 DAVIS Challenge on Video Object Segmentation, the third edition of the DAVIS Challenge series, a public competition designed for the task of Video Object Segmentation (VOS). In addition to the original semi-supervised track and the interactive track introduced in the previous edition, a new unsupervised multi-object track will be featured this year. In the newly introduced track, participants are asked to provide non-overlapping object proposals on each image, along with an identifier linking them between frames (i.e. video object proposals), without any test-time human supervision (no scribbles or masks provided on the test video). In order to do so, we have re-annotated the train and val sets of DAVIS 2017 in a concise way that facilitates the unsupervised track, and created new test-dev and test-challenge sets for the competition. Definitions, rules, and evaluation metrics for the unsupervised track are described in detail in this paper.