ImageNet

E363692

benchmark dataset image dataset visual database

ImageNet is a large-scale visual database widely used for training and benchmarking image classification and computer vision algorithms.

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

All labels observed (8)

Label	Occurrences
ImageNet canonical	8
ImageNet Large Scale Visual Recognition Challenge	5
ILSVRC	1
ILSVRC-2014	1
ImageNet dataset	1
ImageNet-1K	1
ImageNet-21K	1
ImageNet-like datasets	1

How this entity was disambiguated

This entity first appeared as the object of triple T3507277 — 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: ImageNet
Context triple: [AlexNet, dataset, ImageNet]

A. 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.
B. 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.
C. MNIST
MNIST is a widely used benchmark dataset of handwritten digit images commonly employed for training and evaluating image classification algorithms in machine learning and computer vision.
D. Google Brain
Google Brain is a deep learning research team at Google that pioneered many advances in neural networks and artificial intelligence.
E. CLIP
CLIP is an OpenAI model that learns joint representations of images and text, enabling tasks like zero-shot image classification and natural language-based image retrieval.
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: ImageNet
Target entity description: ImageNet is a large-scale visual database widely used for training and benchmarking image classification and computer vision algorithms.

A. 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.
B. 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.
C. MNIST
MNIST is a widely used benchmark dataset of handwritten digit images commonly employed for training and evaluating image classification algorithms in machine learning and computer vision.
D. Google Brain
Google Brain is a deep learning research team at Google that pioneered many advances in neural networks and artificial intelligence.
E. CLIP
CLIP is an OpenAI model that learns joint representations of images and text, enabling tasks like zero-shot image classification and natural language-based image retrieval.
F. None of above. chosen

Statements (51)

Predicate	Object
instanceOf	benchmark dataset ⓘ image dataset ⓘ visual database ⓘ
abbreviation	ILSVRC ⓘ linked to: ImageNet
accessMethod	download upon registration ⓘ
annotatedBy	crowdsourcing ⓘ
annotatedUsing	Amazon Mechanical Turk ⓘ
associatedEvent	ImageNet Large Scale Visual Recognition Challenge ⓘ linked to: ImageNet
basedOn	WordNet ⓘ
commonSplit	test set ⓘ training set ⓘ validation set ⓘ
contains	labeled images ⓘ natural images ⓘ
creator	Fei-Fei Li ⓘ Jia Deng ⓘ Kai Li ⓘ Li Fei-Fei (project lead) ⓘ linked to: Fei-Fei Li
curatedBy	Stanford University researchers ⓘ linked to: Stanford University professors
enabled	deep convolutional neural network advances ⓘ
evaluationMetric	top-1 accuracy ⓘ top-5 accuracy ⓘ
field	artificial intelligence ⓘ computer vision ⓘ machine learning ⓘ
hasIssue	dataset bias ⓘ problematic labels in some categories ⓘ representation bias ⓘ
hasSubset	ImageNet Large Scale Visual Recognition Challenge dataset ⓘ ImageNet-1K ⓘ linked to: ImageNet ImageNet-21K ⓘ linked to: ImageNet
hasTask	image classification task ⓘ object detection task ⓘ object localization task ⓘ
influenced	AlexNet ⓘ GoogLeNet ⓘ ResNet ⓘ VGGNet ⓘ linked to: VGG modern transfer learning practices ⓘ
introduced	2009 ⓘ
license	research-only license ⓘ
notableFor	enabling AlexNet breakthrough in 2012 ⓘ
notableYear	2012 ⓘ
organizesConceptsBy	synsets ⓘ
scale	large-scale ⓘ
typicalImageResolution	256x256 pixels (resized for training) ⓘ
usedFor	benchmarking computer vision algorithms ⓘ image classification ⓘ object recognition ⓘ pretraining deep neural networks ⓘ visual representation learning ⓘ

How these facts were elicited

Referenced by (19)

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

AlexNet → competition → ImageNet Large Scale Visual Recognition Challenge ⓘ

linked to: ImageNet

AlexNet → dataset → ImageNet ⓘ

AlexNet → competitionOrganizer → ImageNet ⓘ

VGG → designedFor → ImageNet Large Scale Visual Recognition Challenge ⓘ

linked to: ImageNet

VGG → trainedOn → ImageNet ⓘ

ResNet → benchmarkedOn → ImageNet ⓘ

torchvision → dataset → ImageNet ⓘ

subject linked to: torchvision (ecosystem)

Alex Krizhevsky → contributedTo → ImageNet Large Scale Visual Recognition Challenge ⓘ

linked to: ImageNet

Alex Krizhevsky → usedDataset → ImageNet ⓘ

Inception Score → commonlyComputedOn → ImageNet-like datasets ⓘ

linked to: ImageNet

ImageNet → hasSubset → ImageNet-1K ⓘ

linked to: ImageNet

ImageNet → hasSubset → ImageNet-21K ⓘ

linked to: ImageNet

ImageNet → associatedEvent → ImageNet Large Scale Visual Recognition Challenge ⓘ

linked to: ImageNet

ImageNet → abbreviation → ILSVRC ⓘ

linked to: ImageNet

Very Deep Convolutional Networks for Large-Scale Image Recognition → benchmark → ImageNet ⓘ

Very Deep Convolutional Networks for Large-Scale Image Recognition → benchmark → ILSVRC-2014 ⓘ

linked to: ImageNet

ResNeXt → evaluatedOn → ImageNet dataset ⓘ

linked to: ImageNet

Fei-Fei Li → knownFor → ImageNet ⓘ

Fei-Fei Li → notableWork → ImageNet Large Scale Visual Recognition Challenge ⓘ

linked to: ImageNet

All labels observed (8)

How this entity was disambiguated Show

Statements (51)

How these facts were elicited Show

Referenced by (19)

How this entity was disambiguated

How these facts were elicited