Images

LVIS

Introduced in LVIS: A Dataset for Large Vocabulary Instance Segmentation

About this Dataset

LVIS is a dataset for long tail instance segmentation. It has annotations for over 1000 object categories in 164k images.

Source: LVIS

Source: LVIS: A Dataset for Large Vocabulary Instance Segmentation

Dataset Variants

LVIS v1.0

LVIS v1.0 val

LVIS v1.0 test-dev

LVIS

LVIS v1.0 minival

Papers1

LVIS: A Dataset for Large Vocabulary Instance Segmentation

This work introduces LVIS (pronounced ‘el-vis’): a new dataset for Large Vocabulary Instance Segmentation, which has a long tail of categories with few training samples due to the Zipfian distribution of categories in natural images.

Dataset Loaders

EDIT

🔥

facebookresearch/detectron2

pytorch

🔥

open-mmlab/mmdetection

pytorch

🎯

tensorflow/datasets

tfjax

Tasks

EDIT

Object Detection Instance Segmentation Few-Shot Object Detection Unsupervised Object Detection Zero-Shot Object Detection Open Vocabulary Object Detection Long-tailed Object Detection Novel Object Detection Zero-Shot Instance Segmentation

Similar Datasets

MNIST

CelebA

JFT-300M

Statistics

Papers

1

Tasks

192

License

Custom (CC BY 4.0 + COCO license)

Modalities

Images