CenterDisks: Real-time instance segmentation with disk covering

arXiv:2403.03296v1 Announce Type: new
Abstract: Increasing the accuracy of instance segmentation methods is often done at the expense of speed. Using coarser representations, we can reduce the number of parameters and thus obtain real-time masks. In this paper, we take inspiration from the set cover problem to predict mask approximations. Given ground-truth binary masks of objects of interest as training input, our method learns to predict the approximate coverage of these objects by disks without supervision on their location or …

abstract accuracy arxiv binary cs.cv ground-truth inspiration instance masks paper parameters real-time reduce segmentation set speed truth type