arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.12482cs.CV
收藏

基于强化学习的视频对象分割自适应ROI生成

Adaptive ROI Generation for Video Object Segmentation Using Reinforcement Learning

Xi’an Jiaotong-Liverpool University(西交利物浦大学);National University of Singapore(新加坡国立大学)

Mingjie Sun, Jimin Xiao, Eng Gee Lim, Yanchu Xie, Jiashi Feng

摘要:

在本文中,我们的目标是解决跨帧序列的半监督视频对象分割的任务,其中只提供第一帧的地面实况分割。挑战在于如何在线更新从第一帧初始化的分割模型自适应和准确,即使在存在多个混乱的情况下或大对象运动。现有的方法依赖于选择感兴趣的区域进行模型更新,然而,这是粗糙和不灵活的,导致性能下降。为了克服这一局限性,我们提出了一种新的方法,利用强化学习选择最佳的适应区域为每帧,根据历史分割信息。RL模型学习采取最佳行动来调整从前一帧推断的感兴趣区域,以进行在线模型更新。为了加快模型的自适应,我们进一步设计了一种新的基于多叉树的探索方法,以快速选择最佳的状态动作对。我们的实验表明,我们的工作将DAVIS 2016数据集上的平均区域相似度提高到87.1%。

英文摘要:

In this paper, we aim to tackle the task of semi-supervised video object segmentation across a sequence of frames where only the ground-truth segmentation of the first frame is provided. The challenges lie in how to online update the segmentation model initialized from the first frame adaptively and accurately, even in presence of multiple confusing instances or large object motion. The existing approaches rely on selecting the region of interest for model update, which however, is rough and inflexible, leading to performance degradation. To overcome this limitation, we propose a novel approach which utilizes reinforcement learning to select optimal adaptation areas for each frame, based on the historical segmentation information. The RL model learns to take optimal actions to adjust the region of interest inferred from the previous frame for online model updating. To speed up the model adaption, we further design a novel multi-branch tree based exploration method to fast select the best state action pairs. Our experiments show that our work improves the state-of-the-art of the mean region similarity on DAVIS 2016 dataset to 87.1%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑