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

All labels observed (14)

Label	Occurrences
ResNet canonical	11
Deep Residual Learning for Image Recognition	6
Deep Residual Learning for Image Recognition (co-author)	1
Pre-activation ResNet	1
ResNet architecture	1
ResNet on ImageNet classification	1
ResNet-101	1
ResNet-152	1
ResNet-18	1
ResNet-34	1
ResNet-50	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 Cambridge ⓘ surface form: Microsoft Research
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	IEEE Computer Society Conference on Computer Vision and Pattern Recognition ⓘ surface form: CVPR 2016
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	ResNet self-linksurface differs ⓘ surface form: Pre-activation ResNet ResNeXt ⓘ ResNet self-linksurface differs ⓘ surface form: ResNet-101 ResNet self-linksurface differs ⓘ surface form: ResNet-152 ResNet self-linksurface differs ⓘ surface form: ResNet-18 ResNet self-linksurface differs ⓘ surface form: ResNet-34 ResNet self-linksurface differs ⓘ surface form: ResNet-50 ResNet self-linksurface differs ⓘ surface form: ResNet-v2 ResNet self-linksurface differs ⓘ surface form: Wide ResNet
implementationAvailableIn	Keras ⓘ MXNet ⓘ PyTorch ⓘ TensorFlow ⓘ
influenced	design of modern computer vision backbones ⓘ
inspired	many subsequent CNN architectures ⓘ
introducedInPaper	ResNet self-linksurface differs ⓘ surface form: Deep Residual Learning for Image Recognition
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 (29)

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 → ResNet self-linksurface differs ⓘ

this entity surface form: Deep Residual Learning for Image Recognition