arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.06647cs.CV
收藏

RANet:用于快速视频对象分割的排名注意力网络

RANet: Ranking Attention Network for Fast Video Object Segmentation

The University of Sydney(悉尼大学);Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University(西安交通大学人工智能与机器人研究所);Inception Institute of Artificial Intelligence (IIAI)(起源人工智能研究院);College of Computer Science, Nankai University(南开大学计算机学院)

Ziqin Wang, Jun Xu, Li Liu, Fan Zhu, Ling Shao

摘要:

尽管在线学习(OL)技术提高了半监督视频对象分割(VOS)方法的性能,但OL巨大的时间开销极大地限制了其实用性。基于匹配和基于传播的方法通过避免OL技术以更快的速度运行。然而,由于不匹配和漂移问题,它们受到次优精度的限制。在本文中,我们开发了一个实时但非常准确的排名注意力网络(RANet)的VOS。具体来说,为了整合基于匹配和基于传播的方法的见解,我们采用编码器-解码器框架以端到端的方式学习像素级相似性和分割。为了更好地利用相似性地图,我们提出了一种新的排名注意力模块,自动排名和选择这些地图细粒度的VOS性能。在DAVIS-16和DAVIS-17数据集上的实验表明,我们的RANet实现了最佳的速度-精度权衡,例如,在DAVIS-16上,每帧33毫秒,J&F=85.5%。使用OL,我们的RANet在DAVIS-16上达到J&F=87.1%,超过了最先进的VOS方法。代码可以在https://github.com/Storife/RANet上找到。

英文摘要:

Despite online learning (OL) techniques have boosted the performance of semi-supervised video object segmentation (VOS) methods, the huge time costs of OL greatly restrict their practicality. Matching based and propagation based methods run at a faster speed by avoiding OL techniques. However, they are limited by sub-optimal accuracy, due to mismatching and drifting problems. In this paper, we develop a real-time yet very accurate Ranking Attention Network (RANet) for VOS. Specifically, to integrate the insights of matching based and propagation based methods, we employ an encoder-decoder framework to learn pixel-level similarity and segmentation in an end-to-end manner. To better utilize the similarity maps, we propose a novel ranking attention module, which automatically ranks and selects these maps for fine-grained VOS performance. Experiments on DAVIS-16 and DAVIS-17 datasets show that our RANet achieves the best speed-accuracy trade-off, e.g., with 33 milliseconds per frame and J&F=85.5% on DAVIS-16. With OL, our RANet reaches J&F=87.1% on DAVIS-16, exceeding state-of-the-art VOS methods. The code can be found at https://github.com/Storife/RANet.

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。

↑