Microsoft COCO: Common Objects in Context

• DOI: 10.48550/arxiv.1405.0312
• Publication Date: 2014-01-01
• Authors: Tsung-Yi Lin; Michael Maire; Serge Belongie; Lubomir Bourdev; Ross Girshick; James Hays; Pietro Perona; Deva Ramanan; C. Lawrence Zitnick; Piotr Dollár
• Keywords: Pascal (unit); Spotting; Bounding overwatch; Minimum bounding box; Baseline (sea)

We present a new dataset with the goal of advancing state-of-the-art in object recognition by placing question context broader scene understanding. This is achieved gathering images complex everyday scenes containing common objects their natural context. Objects are labeled using per-instance segmentations to aid precise localization. Our contains photos 91 types that would be easily recognizable 4 year old. With total 2.5 million instances 328k images, creation our drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and segmentation. detailed statistical analysis comparison PASCAL, ImageNet, SUN. Finally, we provide baseline performance bounding box segmentation detection results Deformable Parts Model.