MASK-RL: Multiagent Video Object Segmentation Framework Through Reinforcement Learning

doi:10.1109/TNNLS.2019.2963282

MASK-RL: Multiagent Video Object Segmentation Framework Through Reinforcement Learning

2020-12-01

22

PRE

AI

Concetto Spampinato *

DOI：10.1109/TNNLS.2019.2963282

Original

Original request for help

Save

Abstract

En 中文

Integrating human-provided location priors into video object segmentation has been shown to be an effective strategy to enhance performance, but their application at large scale is unfeasible. Gamification can help reduce the annotation burden, but it still requires user involvement. We propose a video object segmentation framework that leverages the combined advantages of user feedback for segmentation and gamification strategy by simulating multiple game players through a reinforcement learning (RL) model that reproduces human ability to pinpoint moving objects and using the simulated feedback to drive the decisions of a fully convolutional deep segmentation network. Experimental results on the DAVIS-17 benchmark show that: 1) including user-provided prior, even if not precise, yields high performance; 2) our RL agent replicates satisfactorily the same variability of humans in identifying spatiotemporal salient objects; and 3) employing artificially generated priors in an unsupervised video object segmentation model reaches state-of-the-art performance.

Keywords:

Object segmentation

Annotations

Computational modeling

Games

Motion segmentation

Learning systems

Computer vision

learning systems

machine intelligence

MASK-RL: Multiagent Video Object Segmentation Framework Through Reinforcement Learning

Abstract

AI Summary

Journal

Organization