arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.08270cs.CV
收藏

基于核记忆网络的视频对象分割

Kernelized Memory Network for Video Object Segmentation

Yonsei University(延世大学)

Hongje Seong, Junhyuk Hyun, Euntai Kim

摘要:

半监督视频对象分割(VOS)是一项任务,涉及当在第一帧中给出目标对象的地面真实分割掩码时预测视频中的目标对象。最近,时空记忆网络(STM)作为一种有前途的半监督VOS解决方案受到了极大的关注。然而,在将STM应用于VOS时,忽略了一个重要的问题。解决方案(STM)是非本地的,但问题(VOS)主要是本地的。为了解决STM和VOS之间的不匹配,我们提出了一个内核化的内存网络(KMN)。在对真实视频进行训练之前,我们的KMN在静态图像上进行了预训练,就像以前的作品一样。与以前的作品不同,我们在预训练中使用Hide-and-Seek策略,以获得处理遮挡和段边界提取的最佳结果。拟议的KMN在标准基准上远远超过了最先进的水平(在DAVIS 2017测试开发集上增加了5%)。此外,在DAVIS 2016验证集上,KMN的运行时间为每帧0.12秒,与STM相比,KMN很少需要额外的计算。

英文摘要:

Semi-supervised video object segmentation (VOS) is a task that involves predicting a target object in a video when the ground truth segmentation mask of the target object is given in the first frame. Recently, space-time memory networks (STM) have received significant attention as a promising solution for semi-supervised VOS. However, an important point is overlooked when applying STM to VOS. The solution (STM) is non-local, but the problem (VOS) is predominantly local. To solve the mismatch between STM and VOS, we propose a kernelized memory network (KMN). Before being trained on real videos, our KMN is pre-trained on static images, as in previous works. Unlike in previous works, we use the Hide-and-Seek strategy in pre-training to obtain the best possible results in handling occlusions and segment boundary extraction. The proposed KMN surpasses the state-of-the-art on standard benchmarks by a significant margin (+5% on DAVIS 2017 test-dev set). In addition, the runtime of KMN is 0.12 seconds per frame on the DAVIS 2016 validation set, and the KMN rarely requires extra computation, when compared with STM.

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。

↑