You're currently viewing an old version of this dataset. To see the current version, click here.

LVIS: A Dataset for Large Vocabulary Instance Segmentation

The LVIS dataset is a large-scale object detection and instance segmentation dataset, containing about 2.2 million high-quality instance segmentation masks with a broader spectrum of 1000 class labels.

Data and Resources

This dataset has no data

Cite this as

Agrim Gupta, Piotr Dollar, Ross Girshick (2024). Dataset: LVIS: A Dataset for Large Vocabulary Instance Segmentation. https://doi.org/10.57702/bc95d7b0

Private DOI This DOI is not yet resolvable.
It is available for use in manuscripts, and will be published when the Dataset is made public.

Additional Info

Field	Value
Created	December 2, 2024
Last update	December 2, 2024
Defined In	https://doi.org/10.48550/arXiv.2406.14924
Citation	https://doi.org/10.48550/arXiv.2310.01393
Author	Agrim Gupta
More Authors	Piotr Dollar Ross Girshick
Homepage	https://www.lvisdataset.org/