|
gptkbp:instanceOf
|
gptkb:model
object detection algorithm
|
|
gptkbp:bench
|
gptkb:COCO_dataset
gptkb:PASCAL_VOC
|
|
gptkbp:category
|
gptkb:artificial_intelligence
computer vision
|
|
gptkbp:citation
|
over 20,000
|
|
gptkbp:component
|
region proposal network
backbone network
bounding box regression branch
classification branch
mask branch
|
|
gptkbp:developedBy
|
gptkb:Ross_Girshick
gptkb:Kaiming_He
gptkb:Georgia_Gkioxari
gptkb:Piotr_Dollár
|
|
gptkbp:extendsTo
|
gptkb:Faster_R-CNN
|
|
gptkbp:frameworks
|
gptkb:TensorFlow
gptkb:Keras
gptkb:PyTorch
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Mask R-CNN
|
|
gptkbp:influenced
|
gptkb:Cascade_R-CNN
gptkb:Hybrid_Task_Cascade
gptkb:PANet
|
|
gptkbp:influencedBy
|
gptkb:Faster_R-CNN
|
|
gptkbp:input
|
gptkb:illustrator
|
|
gptkbp:memiliki_tugas
|
object detection
semantic segmentation
instance segmentation
|
|
gptkbp:notableFeature
|
end-to-end training
flexible architecture
pixel-level segmentation
|
|
gptkbp:notablePublication
|
gptkb:Mask_R-CNN
https://arxiv.org/abs/1703.06870
|
|
gptkbp:openSource
|
gptkb:Detectron
gptkb:Matterport_Mask_R-CNN
|
|
gptkbp:output
|
class labels
bounding boxes
segmentation masks
|
|
gptkbp:publicationDate
|
gptkb:Facebook_AI_Research
|
|
gptkbp:publishedIn
|
2017
|
|
gptkbp:usedFor
|
autonomous vehicles
robotics
medical image analysis
video surveillance
|
|
gptkbp:uses
|
gptkb:convolutional_neural_network
gptkb:Region_Proposal_Network
gptkb:RoIAlign
|
|
gptkbp:bfsParent
|
gptkb:convolutional_neural_network
gptkb:Meta_AI
|
|
gptkbp:bfsLayer
|
5
|