Adaptive ROI Generation for Video Object Segmentation Using Reinforcement Learning

•We deploy the “actor critic” RL framework to train the agent for generating the adaptation areas.•W e further design a novel multi branch tree based exploration method to fast select the best state action pairs to speed up the RL training.•New state of the art result of mean re gion similarity is obtained for the DAVIS 2016 dataset, which is 87.1%.