COCO-Stuff: Thing and Stuff Classes in Context

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 1209 - 1218
• Main Authors: Caesar, Holger, Uijlings, Jasper, Ferrari, Vittorio
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Automobiles; Bridges; Image segmentation; Protocols; Semantics; Shape; Vegetation mapping

Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus on thing classes, less attention has been given to stuff classes. Nonetheless, stuff classes ar...