Depth-Guided Semi-Supervised Instance Segmentation

arXiv:2406.17413v1 Announce Type: new
Abstract: Semi-Supervised Instance Segmentation (SSIS) aims to leverage an amount of unlabeled data during training. Previous frameworks primarily utilized the RGB information of unlabeled images to generate pseudo-labels. However, such a mechanism often introduces unstable noise, as a single instance can display multiple RGB values. To overcome this limitation, we introduce a Depth-Guided (DG) SSIS framework. This framework uses depth maps extracted from input images, which represent individual instances with closely associated distance values, offering precise …

abstract arxiv cs.cv data display frameworks generate however images information instance labels multiple noise segmentation semi semi-supervised training type values