Learning Video Object Segmentation from Unlabeled Videos
We propose a new method for video object segmentation (VOS) that addresses object pattern learning from unlabeled videos, unlike most existing methods which rely heavily on extensive annotated data. We introduce a unified unsupervised/weakly supervised learning framework, called MuG, that comprehensively captures intrinsic properties of VOS at multiple granularities. Our approach can help advance understanding of visual patterns in VOS and significantly reduce annotation burden. With a carefully-designed architecture and strong representation learning ability, our learned model can be applied to diverse VOS settings, including object-level zero-shot VOS, instance-level zero-shot VOS, and one-shot VOS. Experiments demonstrate promising performance in these settings, as well as the potential of MuG in leveraging unlabeled data to further improve the segmentation accuracy.
Code (1)
Tasks
ObjectRepresentation LearningSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationUnsupervised Video Object SegmentationVideo Object SegmentationVideo Semantic SegmentationWeakly-supervised LearningSimilar Papers 제목 키워드 기반
Self-Supervised Learning of Object Segmentation from Unlabeled RGB-D Videos
This work proposes a self-supervised learning system for segmenting rigid objects in RGB images. The proposed pipeline is trained on unlabeled RGB-D videos of static objects, which can be captured with a camera carried b…
Contrastive LearningGraph MatchingObjectPoint Cloud Registration+2MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos
Embodied agents must detect and localize objects of interest, e.g. traffic participants for self-driving cars. Supervision in the form of bounding boxes for this task is extremely expensive. As such, prior work has looke…
Motion SegmentationObjectobject-detectionObject Detection+5Semi-Weakly-Supervised Learning of Complex Actions From Instructional Task Videos
We address the problem of action segmentation in instructional task videos with a small number of weakly-labeled training videos and a large number of unlabeled videos, which we refer to as Semi-Weakly-Supervised Lea…
Action SegmentationWeakly-supervised LearningLearning to Better Segment Objects from Unseen Classes with Unlabeled Videos
The ability to localize and segment objects from unseen classes would open the door to new applications, such as autonomous object learning in active vision. Nonetheless, improving the performance on unseen classes requi…
Instance SegmentationObjectOpen-World Instance SegmentationSemantic Segmentation+2Unsupervised Video Object Segmentation with Online Adversarial Self-Tuning
The existing unsupervised video object segmentation methods depend heavily on the segmentation model trained offline on a labeled training video set, and cannot well generalize to the test videos from a different dom…
ObjectPseudo LabelSegmentationSemantic Segmentation+3