Statements (32)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:dataset
|
gptkbp:annotationType |
bounding boxes
category labels polygon masks |
gptkbp:author |
A. Gupta, P. Dollar, R. Girshick, K. He, T. Hariharan, B. Hariharan, S. Kirillov, A. Krishnan, S. Lazebnik, J. Malik, et al.
|
gptkbp:category |
1203
|
gptkbp:citation |
2019
|
gptkbp:domain |
computer vision
|
gptkbp:firstReleased |
2019
|
gptkbp:focus |
instance segmentation
|
gptkbp:format |
COCO JSON
|
gptkbp:fullName |
Large Vocabulary Instance Segmentation
|
https://www.w3.org/2000/01/rdf-schema#label |
LVIS dataset
|
gptkbp:license |
gptkb:Creative_Commons_Attribution_4.0_International
|
gptkbp:notableFeature |
large vocabulary
long-tailed distribution of categories rare categories |
gptkbp:notablePublication |
The LVIS Dataset: A Benchmark for Large Vocabulary Instance Segmentation
https://arxiv.org/abs/1908.03195 |
gptkbp:numberOfAnnotations |
2.2 million
|
gptkbp:numberOfRooms |
164k
|
gptkbp:relatedTo |
gptkb:COCO_dataset
|
gptkbp:releaseYear |
gptkb:Facebook_AI_Research
|
gptkbp:separates |
gptkb:train
examination val |
gptkbp:usedFor |
object recognition
object detection instance segmentation |
gptkbp:website |
https://www.lvisdataset.org/
|
gptkbp:bfsParent |
gptkb:Detectron2
|
gptkbp:bfsLayer |
6
|