论文标题
将运动视为减少无监督视频对象细分运动依赖性的选项
Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
论文作者
论文摘要
无监督的视频对象分割（VOS）旨在在像素级别的视频序列中检测最显着的对象。在无监督的VO中，大多数最先进的方法除了外观提示外，还利用从光流图获得的运动提示来利用与背景相比，显着物体通常具有独特运动的属性。但是，由于它们过于依赖运动提示，在某些情况下可能是不可靠的，因此它们无法实现稳定的预测。为了减少现有两流VOS方法的这种运动依赖性，我们提出了一个新型的运动 - 选项网络，该网络可选地利用运动提示。此外，为了完全利用并非总是需要运动的网络的属性，我们引入了协作网络学习策略。在所有公共基准数据集中，我们提出的网络以实时推理速度提供最先进的性能。
Unsupervised video object segmentation (VOS) aims to detect the most salient object in a video sequence at the pixel level. In unsupervised VOS, most state-of-the-art methods leverage motion cues obtained from optical flow maps in addition to appearance cues to exploit the property that salient objects usually have distinctive movements compared to the background. However, as they are overly dependent on motion cues, which may be unreliable in some cases, they cannot achieve stable prediction. To reduce this motion dependency of existing two-stream VOS methods, we propose a novel motion-as-option network that optionally utilizes motion cues. Additionally, to fully exploit the property of the proposed network that motion is not always required, we introduce a collaborative network learning strategy. On all the public benchmark datasets, our proposed network affords state-of-the-art performance with real-time inference speed.
