数据集图片数量比较

COCO-Caption有33万张图、50万个caption
COCO-Stuff有16.4万张图 172个类别(80thing、91stuff、1个未标注类)

COCO-stuff的具体类别说明

COCO-Stuff contains 172 classes:
80 thing, 91 stuff, and 1 class unlabeled.
The 80 thing classes are the same as in COCO [35].
The 91 stuff classes are curated by an expert annotator.
The class unlabeled is used in two situations:
if a label does not belong to any of the 171 predefined classes, or if the annotator cannot infer the label of a pixel.
如果标签不属于171个预定义类中的任何一个，或者注释器不能推断像素的标签。

图1：（左&#x