|
gptkbp:instance_of
|
gptkb:Model
|
|
gptkbp:bfsLayer
|
5
|
|
gptkbp:bfsParent
|
gptkb:Faster_R-CNN
gptkb:R-CNN
|
|
gptkbp:applies_to
|
end-to-end training
|
|
gptkbp:based_on
|
convolutional neural networks
|
|
gptkbp:developed_by
|
gptkb:Ross_B._Girshick
gptkb:Stanford_University
|
|
gptkbp:has_achievements
|
state-of-the-art accuracy
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Fast R-CNN
|
|
gptkbp:improves
|
gptkb:feature_pyramid_networks
gptkb:R-CNN
|
|
gptkbp:input_output
|
bounding box predictions
class scores
|
|
gptkbp:is_adopted_by
|
gptkb:Educational_Institution
government agencies
industry leaders
research institutions
startups
|
|
gptkbp:is_cited_in
|
numerous research papers
|
|
gptkbp:is_compared_to
|
gptkb:CEO
gptkb:YOLO
|
|
gptkbp:is_effective_against
|
SP Pnet
|
|
gptkbp:is_evaluated_by
|
MSCOCO dataset
PASCALVOC dataset
mean average precision (m AP)
intersection over union (Io U)
|
|
gptkbp:is_implemented_in
|
gptkb:Caffe
|
|
gptkbp:is_influenced_by
|
gptkb:Res_Net
gptkb:Alex_Net
VGG Net
|
|
gptkbp:is_optimized_for
|
real-time applications
|
|
gptkbp:is_part_of
|
machine learning applications
deep learning frameworks
AI technologies
deep learning models
computer vision research
|
|
gptkbp:is_related_to
|
data augmentation
image classification
transfer learning
object localization
|
|
gptkbp:is_supported_by
|
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch
|
|
gptkbp:is_used_for
|
pedestrian detection
face detection
object tracking
animal detection
vehicle detection
|
|
gptkbp:is_used_in
|
gptkb:Photographer
gptkb:robot
gptkb:engine
augmented reality
surveillance systems
image segmentation
computer vision tasks
|
|
gptkbp:published_by
|
gptkb:ar_Xiv
|
|
gptkbp:release_year
|
gptkb:2015
|
|
gptkbp:requires
|
GPU for training
|
|
gptkbp:speed
|
gptkb:R-CNN
|
|
gptkbp:training
|
large datasets
|
|
gptkbp:uses
|
region proposal networks
|