Statements (101)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:AI_technology
|
| gptkbp:adapted_into |
different domains
|
| gptkbp:adds |
pixel-level segmentation
|
| gptkbp:applies_to |
Ro IAlign
|
| gptkbp:based_on |
gptkb:Faster_R-CNN
|
| gptkbp:can_be_used_for |
video analysis
image segmentation |
| gptkbp:can_detect |
multiple classes
|
| gptkbp:competes_with |
gptkb:SSD
gptkb:YOLO |
| gptkbp:developed_by |
gptkb:Facebook_AI_Research
|
| gptkbp:enhances |
image segmentation accuracy
|
| gptkbp:has |
open-source implementations
backbone networks |
| gptkbp:has_achieved |
state-of-the-art results
|
| gptkbp:has_applications_in |
gptkb:robotics
augmented reality image editing |
| gptkbp:has_expansion |
gptkb:Faster_R-CNN
|
| https://www.w3.org/2000/01/rdf-schema#label |
Mask R-CNN
|
| gptkbp:improves |
gptkb:Faster_R-CNN
pixel-level segmentation |
| gptkbp:input_output |
bounding boxes
segmentation masks |
| gptkbp:introduced_in |
gptkb:2017
|
| gptkbp:is_adopted_by |
research institutions
industry applications tech companies academic research. |
| gptkbp:is_applied_in |
gptkb:medical_imaging
autonomous driving video analysis |
| gptkbp:is_compatible_with |
transfer learning
|
| gptkbp:is_considered_as |
a standard in segmentation tasks
|
| gptkbp:is_discussed_in |
online forums
|
| gptkbp:is_documented_in |
research papers
academic papers Git Hub repositories |
| gptkbp:is_evaluated_by |
gptkb:Cityscapes_dataset
gptkb:KITTI_dataset competitions cross-validation benchmark datasets m AP (mean Average Precision) Io U (Intersection over Union) Io U metric m AP metric |
| gptkbp:is_implemented_in |
gptkb:Tensor_Flow
gptkb:Py_Torch |
| gptkbp:is_influenced_by |
gptkb:R-CNN
gptkb:Na'vi gptkb:Seg_Net |
| gptkbp:is_influential_in |
deep learning community
|
| gptkbp:is_known_for |
flexibility
high accuracy robustness flexibility in tasks |
| gptkbp:is_often_used_in |
computer vision
|
| gptkbp:is_optimized_for |
gptkb:Speed
accuracy data augmentation transfer learning |
| gptkbp:is_part_of |
AI research projects
computer vision frameworks computer vision toolkit |
| gptkbp:is_popular_in |
gptkb:academic_research
industry applications computer vision community |
| gptkbp:is_related_to |
image classification
feature extraction object recognition semantic segmentation |
| gptkbp:is_scalable |
large images
|
| gptkbp:is_supported_by |
community contributions
|
| gptkbp:is_taught_in |
university courses
|
| gptkbp:is_trained_in |
gptkb:COCO_dataset
gptkb:Pascal_VOC_dataset |
| gptkbp:is_used_for |
scene understanding
face detection image captioning |
| gptkbp:is_used_in |
gptkb:medical_imaging
gptkb:vehicles gptkb:robotics augmented reality surveillance systems object tracking image segmentation competitions |
| gptkbp:provides |
pixel-wise predictions
|
| gptkbp:requires |
convolutional neural networks
GPU for training large datasets for training |
| gptkbp:suitable_for |
real-time applications
|
| gptkbp:supports |
multi-task learning
|
| gptkbp:training |
backpropagation
stochastic gradient descent |
| gptkbp:used_for |
object detection
instance segmentation |
| gptkbp:uses |
Fully Convolutional Networks
|
| gptkbp:utilizes |
Region Proposal Network
|
| gptkbp:bfsParent |
gptkb:neural_networks
|
| gptkbp:bfsLayer |
4
|