PM-VIS: High-Performance Box-Supervised Video Instance Segmentation

arXiv:2404.13863v1 Announce Type: new
Abstract: Labeling pixel-wise object masks in videos is a resource-intensive and laborious process. Box-supervised Video Instance Segmentation (VIS) methods have emerged as a viable solution to mitigate the labor-intensive annotation process. . In practical applications, the two-step approach is not only more flexible but also exhibits a higher recognition accuracy. Inspired by the recent success of Segment Anything Model (SAM), we introduce a novel approach that aims at harnessing instance box annotations from multiple perspectives to …

abstract accuracy annotation applications arxiv box cs.cv instance labeling labor masks object performance pixel practical process recognition segmentation solution type video video instance segmentation videos wise