arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.11655cs.CV
收藏

半监督视频对象分割中基于复用门函数的学习动态网络

Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation

Seoul National University(首尔国立大学);Facebook Inc.(脸书公司);AIRS Company, Hyundai Motor Group(现代汽车集团AIRS公司)

Hyojin Park, Jayeon Yoo, Seohyeong Jeong, Ganesh Venkatesh, Nojun Kwak

摘要:

当前用于半监督视频对象分割(Semi-VOS)的现有技术方法传播来自先前帧的信息以生成用于当前帧的分割掩模。这可以在具有挑战性的场景中实现高质量的分割,例如外观和遮挡的变化。但它也会导致对静止或缓慢移动的对象进行不必要的计算,这些对象在帧间的变化很小。在这项工作中,我们利用这一观察,使用时间信息,以快速识别帧与最小的变化,跳过重量级掩码生成步骤。为了实现这种效率,我们提出了一种新的动态网络,它可以估计帧间的变化,并根据预期的相似性决定选择哪条路径-计算完整的网络或重用前一帧的特征。实验结果表明,我们的方法在具有挑战性的Semi-VOS数据集(DAVIS 16,DAVIS 17和YouTube-VOS)上显着提高了推理速度,而不会降低准确性。此外,我们的方法可以应用于多个半VOS方法,证明其通用性。该代码可在https://github.com/HYOJINPARK/Reuse_VOS上获得。

英文摘要:

Current state-of-the-art approaches for Semi-supervised Video Object Segmentation (Semi-VOS) propagates information from previous frames to generate segmentation mask for the current frame. This results in high-quality segmentation across challenging scenarios such as changes in appearance and occlusion. But it also leads to unnecessary computations for stationary or slow-moving objects where the change across frames is minimal. In this work, we exploit this observation by using temporal information to quickly identify frames with minimal change and skip the heavyweight mask generation step. To realize this efficiency, we propose a novel dynamic network that estimates change across frames and decides which path -- computing a full network or reusing previous frame's feature -- to choose depending on the expected similarity. Experimental results show that our approach significantly improves inference speed without much accuracy degradation on challenging Semi-VOS datasets -- DAVIS 16, DAVIS 17, and YouTube-VOS. Furthermore, our approach can be applied to multiple Semi-VOS methods demonstrating its generality. The code is available in https://github.com/HYOJINPARK/Reuse_VOS.

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。

↑