Learning Transferable Architectures for Scalable Image Recognition

E499148

computer vision paper research paper

"Learning Transferable Architectures for Scalable Image Recognition" is a research paper that introduced NASNet, a neural architecture search–designed convolutional network that achieved state-of-the-art performance on large-scale image recognition tasks.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (1)

Label	Occurrences
Learning Transferable Architectures for Scalable Image Recognition canonical	2

Statements (42)

Predicate	Object
instanceOf	computer vision paper ⓘ research paper ⓘ
application	image classification benchmarks ⓘ transfer learning for vision tasks ⓘ
architectureType	convolutional neural network architecture ⓘ
category	image classification literature ⓘ neural architecture search literature ⓘ
contribution	scalable image recognition architectures ⓘ search on small dataset and transfer to large dataset ⓘ transferable convolutional cell architectures ⓘ
dataset	CIFAR-10 NERFINISHED ⓘ ImageNet NERFINISHED ⓘ
demonstrates	efficient architecture transfer from CIFAR-10 to ImageNet ⓘ state-of-the-art accuracy on ImageNet at time of publication ⓘ
evaluates	accuracy versus computational cost of architectures ⓘ
field	computer vision ⓘ deep learning ⓘ machine learning ⓘ
focusesOn	automated neural network architecture design ⓘ large-scale image classification ⓘ
impact	influenced later neural architecture search methods ⓘ popularized NASNet architectures ⓘ used as baseline in many NAS studies ⓘ
introduces	NASNet-A NERFINISHED ⓘ NASNet-B NERFINISHED ⓘ NASNet-C NERFINISHED ⓘ
introducesConcept	normal cell in NASNet ⓘ reduction cell in NASNet ⓘ
method	neural architecture search with reinforcement learning ⓘ
optimizationObjective	improve accuracy-computation trade-off on ImageNet ⓘ maximize validation accuracy on CIFAR-10 ⓘ
proposes	NASNet NERFINISHED ⓘ
researchArea	convolutional neural networks ⓘ image recognition ⓘ neural architecture search ⓘ
shortTitle	NASNet paper ⓘ
shows	searched architectures outperform hand-designed architectures on ImageNet ⓘ searched cells can be stacked to form deep networks ⓘ
title	Learning Transferable Architectures for Scalable Image Recognition NERFINISHED ⓘ
uses	cell-based search space ⓘ controller recurrent neural network ⓘ reinforcement learning for architecture search ⓘ

Referenced by (2)

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

Barret Zoph → notableWork → Learning Transferable Architectures for Scalable Image Recognition ⓘ

Barret Zoph → authorOf → Learning Transferable Architectures for Scalable Image Recognition ⓘ