ImageNet Classification with Deep Convolutional Neural Networks

E554013

computer vision paper research paper

"ImageNet Classification with Deep Convolutional Neural Networks" is the landmark 2012 research paper that introduced the deep CNN model AlexNet, demonstrating a dramatic leap in image recognition performance on the ImageNet benchmark and catalyzing the modern deep learning revolution in computer vision.

Try in SPARQL Jump to: Statements Referenced by

Statements (48)

Predicate	Object
instanceOf	computer vision paper ⓘ research paper ⓘ
benchmark	ILSVRC-2010 NERFINISHED ⓘ ILSVRC-2012 ⓘ
considered	catalyst of the deep learning revolution in vision ⓘ landmark paper in deep learning ⓘ
field	computer vision ⓘ deep learning ⓘ machine learning ⓘ
focusesOn	image classification ⓘ
hasAbbreviation	AlexNet NERFINISHED ⓘ
hasAuthor	Alex Krizhevsky NERFINISHED ⓘ Geoffrey E. Hinton NERFINISHED ⓘ Ilya Sutskever NERFINISHED ⓘ
hasCitationVenueAbbreviation	NIPS 2012 NERFINISHED ⓘ
hasShortName	AlexNet paper NERFINISHED ⓘ
improvementOverStateOfTheArtTop5Error	more than 10 percentage points ⓘ
influencedField	large-scale neural network training on GPUs ⓘ modern deep learning in computer vision ⓘ
inputImageResolution	224x224 pixels ⓘ
introducesModel	AlexNet NERFINISHED ⓘ
introducesTechnique	ReLU nonlinearity in large-scale vision CNNs ⓘ data augmentation for image classification ⓘ dropout for fully connected layers ⓘ local response normalization ⓘ overlapping max pooling ⓘ
language	English ⓘ
numberOfConvolutionalLayersInModel	5 ⓘ
numberOfFullyConnectedLayersInModel	3 ⓘ
numberOfLayersInModel	8 ⓘ
parallelizationStrategy	model parallelism across two GPUs ⓘ
presentedAt	NeurIPS 2012 NERFINISHED ⓘ
proposesArchitectureType	deep convolutional neural network ⓘ
publicationYear	2012 ⓘ
publishedIn	Advances in Neural Information Processing Systems 25 NERFINISHED ⓘ
task	ImageNet Large Scale Visual Recognition Challenge classification NERFINISHED ⓘ
top5ErrorRateOnILSVRC2012	15.3% ⓘ
usesActivationFunction	ReLU ⓘ
usesDataAugmentation	RGB intensity alterations ⓘ horizontal reflections ⓘ random crops ⓘ
usesDataset	ImageNet NERFINISHED ⓘ
usesHardware	GPU ⓘ NVIDIA GTX 580 NERFINISHED ⓘ
usesNumberOfGPUs	2 ⓘ
usesOptimizationAlgorithm	stochastic gradient descent ⓘ
usesRegularization	dropout ⓘ weight decay ⓘ

Referenced by (2)

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

Alex Krizhevsky → coAuthorOf → ImageNet Classification with Deep Convolutional Neural Networks ⓘ

Alex Krizhevsky → notableWork → ImageNet Classification with Deep Convolutional Neural Networks ⓘ