COCONut: Modernizing COCO Segmentation

arXiv:2404.08639v1 Announce Type: new
Abstract: In recent decades, the vision community has witnessed remarkable progress in visual recognition, partially owing to advancements in dataset benchmarks. Notably, the established COCO benchmark has propelled the development of modern detection and segmentation systems. However, the COCO segmentation benchmark has seen comparatively slow improvement over the last decade. Originally equipped with coarse polygon annotations for thing instances, it gradually incorporated coarse superpixel annotations for stuff regions, which were subsequently heuristically amalgamated to yield panoptic …

abstract arxiv benchmark benchmarks coco community cs.cv dataset detection development however improvement modern progress recognition segmentation systems type vision visual