ResNet

E74928

convolutional neural network architecture deep learning model residual network

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.

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

AI illustration

All labels observed (16)

Label	Occurrences
ResNet canonical	14
Deep Residual Learning for Image Recognition	6
ResNet-101	4
ResNet-50	4
Deep Residual Learning for Image Recognition (co-author)	1
Pre-activation ResNet	1
ResNet architecture	1
ResNet architectures	1
ResNet on ImageNet classification	1
ResNet-152	1
ResNet-18	1
ResNet-34	1
ResNet-50-FPN	1
ResNet-v2	1
Wide ResNet	1
residual networks	1

How this entity was disambiguated

This entity first appeared as the object of triple T591899 — 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: ResNet
Context triple: [LeNet, influenced, ResNet]

A. AlexNet
AlexNet is a pioneering deep convolutional neural network architecture that dramatically advanced image recognition performance and helped spark the modern deep learning revolution after winning the 2012 ImageNet competition.
B. VGG
VGG is a deep convolutional neural network architecture known for its simple, uniform use of small 3×3 filters and great depth, which achieved strong performance in image recognition tasks.
C. LeNet
LeNet is one of the earliest convolutional neural network architectures, pioneering modern deep learning approaches to image recognition and handwritten digit classification.
D. CIFAR
CIFAR (the Canadian Institute for Advanced Research) is a Canadian global research organization that supports long-term, collaborative, interdisciplinary research, including major initiatives in artificial intelligence.
E. RBM
RBM is a global partnership initiative dedicated to coordinating and scaling up efforts to prevent, control, and ultimately eliminate malaria worldwide.
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: ResNet
Target entity description: 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.

A. AlexNet
AlexNet is a pioneering deep convolutional neural network architecture that dramatically advanced image recognition performance and helped spark the modern deep learning revolution after winning the 2012 ImageNet competition.
B. VGG
VGG is a deep convolutional neural network architecture known for its simple, uniform use of small 3×3 filters and great depth, which achieved strong performance in image recognition tasks.
C. LeNet
LeNet is one of the earliest convolutional neural network architectures, pioneering modern deep learning approaches to image recognition and handwritten digit classification.
D. CIFAR
CIFAR (the Canadian Institute for Advanced Research) is a Canadian global research organization that supports long-term, collaborative, interdisciplinary research, including major initiatives in artificial intelligence.
E. RBM
RBM is a global partnership initiative dedicated to coordinating and scaling up efforts to prevent, control, and ultimately eliminate malaria worldwide.
F. None of above. chosen

Statements (55)

Predicate	Object
instanceOf	convolutional neural network architecture ⓘ deep learning model ⓘ residual network ⓘ
achievedResult	state-of-the-art performance on ImageNet at introduction ⓘ
addresses	degradation problem in deep networks ⓘ vanishing gradient problem ⓘ
affiliationOfAuthors	Microsoft Research ⓘ linked to: Microsoft Research Cambridge
benchmarkedOn	CIFAR-10 ⓘ CIFAR-100 ⓘ ImageNet ⓘ
developedBy	Jian Sun ⓘ Kaiming He ⓘ Shaoqing Ren ⓘ Xiangyu Zhang ⓘ
domain	computer vision ⓘ
enables	training of very deep networks ⓘ
field	deep learning ⓘ
firstPublishedVenue	CVPR 2016 ⓘ linked to: IEEE Computer Society Conference on Computer Vision and Pattern Recognition
firstPublishedYear	2015 ⓘ
hasArchitectureDepth	101 layers ⓘ 152 layers ⓘ 18 layers ⓘ 34 layers ⓘ 50 layers ⓘ
hasConnectionType	identity skip connection ⓘ projection shortcut ⓘ
hasKeyIdea	identity mappings ⓘ residual learning ⓘ skip connections ⓘ
hasVariant	Pre-activation ResNet ⓘ linked to: ResNet ResNeXt ⓘ ResNet-101 ⓘ linked to: ResNet ResNet-152 ⓘ linked to: ResNet ResNet-18 ⓘ linked to: ResNet ResNet-34 ⓘ linked to: ResNet ResNet-50 ⓘ linked to: ResNet ResNet-v2 ⓘ linked to: ResNet Wide ResNet ⓘ linked to: ResNet
implementationAvailableIn	Keras ⓘ MXNet ⓘ PyTorch ⓘ TensorFlow ⓘ
influenced	design of modern computer vision backbones ⓘ
inspired	many subsequent CNN architectures ⓘ
introducedInPaper	Deep Residual Learning for Image Recognition ⓘ linked to: ResNet
optimizationBenefit	eases optimization of deep networks ⓘ
trainingMethod	stochastic gradient descent ⓘ
usedAs	backbone network in detection models ⓘ
usedFor	feature extraction ⓘ image classification ⓘ object detection ⓘ
usesComponent	ReLU activation ⓘ batch normalization ⓘ convolutional layer ⓘ residual block ⓘ

How these facts were elicited

Referenced by (40)

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

LeNet → influenced → ResNet ⓘ

AlexNet → influenced → ResNet ⓘ

VGG → influenced → ResNet ⓘ

ResNet → introducedInPaper → Deep Residual Learning for Image Recognition ⓘ

linked to: ResNet

ResNet → hasVariant → ResNet-18 ⓘ

linked to: ResNet

ResNet → hasVariant → ResNet-34 ⓘ

linked to: ResNet

ResNet → hasVariant → ResNet-50 ⓘ

linked to: ResNet

ResNet → hasVariant → ResNet-101 ⓘ

linked to: ResNet

ResNet → hasVariant → ResNet-152 ⓘ

linked to: ResNet

ResNet → hasVariant → Wide ResNet ⓘ

linked to: ResNet

ResNet → hasVariant → Pre-activation ResNet ⓘ

linked to: ResNet

ResNet → hasVariant → ResNet-v2 ⓘ

linked to: ResNet

torchvision → modelFamily → ResNet ⓘ

subject linked to: torchvision (ecosystem)

CLIP → imageEncoderType → ResNet ⓘ

ImageNet → influenced → ResNet ⓘ

Kaiming He → knownFor → ResNet ⓘ

Kaiming He → notableWork → Deep Residual Learning for Image Recognition ⓘ

linked to: ResNet

Xiangyu Zhang → notableWork → Deep Residual Learning for Image Recognition (co-author) ⓘ

linked to: ResNet

ResNeXt → basedOn → ResNet ⓘ

ResNeXt → outperforms → ResNet on ImageNet classification ⓘ

linked to: ResNet

ResNeXt → relatedTo → ResNet ⓘ

Shaoqing Ren → knownFor → ResNet ⓘ

Shaoqing Ren → coAuthorOf → Deep Residual Learning for Image Recognition ⓘ

linked to: ResNet

Shaoqing Ren → coDeveloperOf → ResNet architecture ⓘ

linked to: ResNet

Shaoqing Ren → notableWork → Deep Residual Learning for Image Recognition ⓘ

linked to: ResNet

Shaoqing Ren → algorithmTypeWorkedOn → residual networks ⓘ

linked to: ResNet

Jian Sun → notableWork → ResNet ⓘ

Jian Sun → coAuthorOf → Deep Residual Learning for Image Recognition ⓘ

linked to: ResNet

Jian Sun → notablePublication → Deep Residual Learning for Image Recognition ⓘ

linked to: ResNet

DenseNet → differsFrom → ResNet ⓘ

DenseNet → relatedTo → ResNet ⓘ

Faster R-CNN → typicalBackbone → ResNet-50 ⓘ

subject linked to: FasterRCNN

linked to: ResNet

Faster R-CNN → typicalBackbone → ResNet-101 ⓘ

subject linked to: FasterRCNN

linked to: ResNet

Mask R-CNN → commonlyUsedBackbone → ResNet-50 ⓘ

subject linked to: MaskRCNN

linked to: ResNet

Mask R-CNN → commonlyUsedBackbone → ResNet-101 ⓘ

subject linked to: MaskRCNN

linked to: ResNet

RetinaNet → hasBackbone → ResNet ⓘ

RetinaNet → hasBackbone → ResNet-50 ⓘ

linked to: ResNet

RetinaNet → hasBackbone → ResNet-101 ⓘ

linked to: ResNet

KeypointRCNN → typicalBackbone → ResNet-50-FPN ⓘ

linked to: ResNet

Group Normalization → oftenUsedWith → ResNet architectures ⓘ

linked to: ResNet

All labels observed (16)

How this entity was disambiguated Show

Statements (55)

How these facts were elicited Show

Referenced by (40)

How this entity was disambiguated

How these facts were elicited