FasterRCNN

E431008

computer vision model convolutional neural network model deep learning model object detection architecture two-stage detector

FasterRCNN is a popular two-stage object detection architecture that first proposes candidate regions and then classifies and refines bounding boxes, widely used in computer vision tasks.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

All labels observed (7)

Label	Occurrences
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks	3
Faster R-CNN	2
Faster R-CNN (paper)	1
Faster R-CNN architecture	1
FasterRCNN canonical	1
Region Proposal Networks	1
advances in object detection with region-based CNNs	1

How this entity was disambiguated

This entity first appeared as the object of triple T4326003 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: FasterRCNN
Context triple: [torchvision, modelFamily, FasterRCNN]

A. YOLO
"YOLO" is a comedic hip-hop song and music video by The Lonely Island, featuring Adam Levine and Kendrick Lamar, that parodies the phrase "you only live once" by humorously promoting extreme caution and risk avoidance.
B. DETR
DETR is the acronym for the former UK government Department of the Environment, Transport and the Regions, which was responsible for environmental policy, transport, and regional affairs.
C. ResNet
ResNet is a deep convolutional neural network architecture known for its use of residual connections to enable very deep models and achieve state-of-the-art performance in image recognition tasks.
D. Very Deep Convolutional Networks for Large-Scale Image Recognition
"Very Deep Convolutional Networks for Large-Scale Image Recognition" is the influential 2014 research paper that introduced the VGG family of deep convolutional neural network architectures, demonstrating that significantly increasing network depth with small convolutional filters leads to substantial improvements in image classification performance.
E. ResNeXt
ResNeXt is a deep convolutional neural network architecture that extends ResNet by using grouped convolutions and a split-transform-merge strategy to improve accuracy and efficiency in image recognition tasks.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: FasterRCNN
Target entity description: FasterRCNN is a popular two-stage object detection architecture that first proposes candidate regions and then classifies and refines bounding boxes, widely used in computer vision tasks.

A. YOLO
"YOLO" is a comedic hip-hop song and music video by The Lonely Island, featuring Adam Levine and Kendrick Lamar, that parodies the phrase "you only live once" by humorously promoting extreme caution and risk avoidance.
B. DETR
DETR is the acronym for the former UK government Department of the Environment, Transport and the Regions, which was responsible for environmental policy, transport, and regional affairs.
C. ResNet
ResNet is a deep convolutional neural network architecture known for its use of residual connections to enable very deep models and achieve state-of-the-art performance in image recognition tasks.
D. Very Deep Convolutional Networks for Large-Scale Image Recognition
"Very Deep Convolutional Networks for Large-Scale Image Recognition" is the influential 2014 research paper that introduced the VGG family of deep convolutional neural network architectures, demonstrating that significantly increasing network depth with small convolutional filters leads to substantial improvements in image classification performance.
E. ResNeXt
ResNeXt is a deep convolutional neural network architecture that extends ResNet by using grouped convolutions and a split-transform-merge strategy to improve accuracy and efficiency in image recognition tasks.
F. None of above. chosen

Statements (53)

Predicate	Object
instanceOf	computer vision model ⓘ convolutional neural network model ⓘ deep learning model ⓘ object detection architecture ⓘ two-stage detector ⓘ
category	region-based object detector ⓘ
codeAvailableIn	Caffe NERFINISHED ⓘ PyTorch NERFINISHED ⓘ TensorFlow NERFINISHED ⓘ
commonlyUsedIn	autonomous driving perception ⓘ general object detection benchmarks ⓘ medical image analysis ⓘ surveillance systems ⓘ
designedFor	bounding box localization ⓘ object classification in images ⓘ object detection ⓘ
evaluationMetric	mean Average Precision ⓘ
extends	Fast R-CNN NERFINISHED ⓘ R-CNN NERFINISHED ⓘ
fullName	Faster Region-based Convolutional Neural Network NERFINISHED ⓘ
hasComponent	ROI pooling layer ⓘ Region Proposal Network NERFINISHED ⓘ backbone CNN ⓘ bounding box regression head ⓘ classification head ⓘ
improvesOver	Fast R-CNN NERFINISHED ⓘ Selective Search region proposals ⓘ
influenced	Feature Pyramid Networks based detectors NERFINISHED ⓘ Mask R-CNN NERFINISHED ⓘ
introducedInPaper	Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks NERFINISHED ⓘ
keyIdea	learn region proposals with a neural network ⓘ share convolutional features between detection and proposal generation ⓘ
output	object class labels ⓘ refined bounding boxes ⓘ
proposalType	class-agnostic region proposals ⓘ
proposedBy	Jian Sun NERFINISHED ⓘ Kaiming He NERFINISHED ⓘ Ross Girshick NERFINISHED ⓘ Shaoqing Ren NERFINISHED ⓘ
publishedAtConference	NeurIPS 2015 NERFINISHED ⓘ
publishedYear	2015 ⓘ
stage1	Region Proposal Network NERFINISHED ⓘ
stage2	Fast R-CNN style detector ⓘ
trainingDataset	MS COCO NERFINISHED ⓘ PASCAL VOC NERFINISHED ⓘ
typicalBackbone	ResNet-101 NERFINISHED ⓘ ResNet-50 NERFINISHED ⓘ VGG16 NERFINISHED ⓘ
uses	Region Proposal Network NERFINISHED ⓘ anchor boxes ⓘ multi-task loss ⓘ shared convolutional feature maps ⓘ stochastic gradient descent ⓘ

How these facts were elicited

Referenced by (10)

Full triples — surface form annotated when it differs from this entity's canonical label.

torchvision (ecosystem) → modelFamily → FasterRCNN ⓘ

subject surface form: torchvision

Kaiming He → knownFor → FasterRCNN ⓘ

this entity surface form: Faster R-CNN

Kaiming He → notableWork → FasterRCNN ⓘ

this entity surface form: Faster R-CNN (paper)

Kaiming He → notableContribution → FasterRCNN ⓘ

this entity surface form: advances in object detection with region-based CNNs

Shaoqing Ren → knownFor → FasterRCNN ⓘ

this entity surface form: Faster R-CNN

Shaoqing Ren → coAuthorOf → FasterRCNN ⓘ

this entity surface form: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Shaoqing Ren → coDeveloperOf → FasterRCNN ⓘ

this entity surface form: Faster R-CNN architecture

Shaoqing Ren → contributedTo → FasterRCNN ⓘ

this entity surface form: Region Proposal Networks

Shaoqing Ren → notableWork → FasterRCNN ⓘ

this entity surface form: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Jian Sun → notablePublication → FasterRCNN ⓘ

this entity surface form: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

All labels observed (7)

How this entity was disambiguated Show

Statements (53)

How these facts were elicited Show

Referenced by (10)

How this entity was disambiguated

How these facts were elicited