COCO的 全称是Common Objects in COntext,是微软团队提供的一个可以用来进行图像识别的数据集。MS COCO数据集中的图像分为训练、验证和测试集。
COCO is a large-scale object detection, segmentation, and captioning dataset. COCO has several features:
Object segmentation Recognition in context Superpixel stuff segmentation 330K images (>200K labeled) 1.5 million object instances 80 object categories 91 stuff categories 5 captions per image 250,000 people with keypoints