COCO-Thing-Stuff

The COCO-Thing-Stuff dataset is used for the L2I task, which includes 118,287 training images and 5,000 validation images. Each image is annotated with bounding boxes and pixel-level segmentation masks for 80 categories of objects and 91 categories of stuff.

Data and Resources

Cite this as

Yibo Wang, Ruiyuan Gao, Kai Chen, Kaiqiang Zhou, Yingjie Cai, Lanqing Hong, Zhenguo Li, Dit-Yan Yeung, Qiang Xu, Kai Zhang (2024). Dataset: COCO-Thing-Stuff. https://doi.org/10.57702/07h2ml7o

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2403.13304
Author Yibo Wang
More Authors
Ruiyuan Gao
Kai Chen
Kaiqiang Zhou
Yingjie Cai
Lanqing Hong
Zhenguo Li
Dit-Yan Yeung
Qiang Xu
Kai Zhang
Homepage https://ai.stanford.edu/~jkrause/coco-thing.html