Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
This addresses the issue of unstable predictions in video object segmentation for computer vision applications, representing an incremental improvement over existing two-stream methods.
The paper tackled the problem of motion dependency in unsupervised video object segmentation by proposing a motion-as-option network that optionally uses motion cues, achieving state-of-the-art performance on all public benchmark datasets with real-time inference speed.
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.