ResNeXt

E367297

convolutional neural network architecture deep learning model image recognition architecture

ResNeXt is a deep convolutional neural network architecture that extends ResNet by using grouped convolutions and a split-transform-merge strategy to improve accuracy and efficiency in image recognition tasks.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (6)

Label	Occurrences
ResNeXt canonical	1
ResNeXt architecture	1
ResNeXt-101	1
ResNeXt-152	1
ResNeXt-50	1
ResNeXt: Aggregated Residual Transformations for Deep Neural Networks	1

Statements (48)

Predicate	Object
instanceOf	convolutional neural network architecture ⓘ deep learning model ⓘ image recognition architecture ⓘ
aimsTo	improve accuracy in image recognition tasks ⓘ improve computational efficiency ⓘ
appliedIn	feature extraction for vision tasks ⓘ image classification ⓘ object detection backbones ⓘ
basedOn	ResNet ⓘ
compatibleWith	GPU acceleration ⓘ
controlsComplexityBy	fixing total computational cost while varying cardinality ⓘ
evaluatedOn	CIFAR-10 ⓘ surface form: CIFAR-10 dataset CIFAR-100 ⓘ surface form: CIFAR-100 dataset ImageNet ⓘ surface form: ImageNet dataset
extends	ResNet bottleneck block design ⓘ residual learning framework ⓘ
firstPublishedYear	2017 ⓘ
hasCodeRepository	https://github.com/facebookresearch/ResNeXt ⓘ
hasDesignElement	aggregated residual transformations ⓘ merge stage ⓘ multiple parallel transformation paths ⓘ split stage ⓘ transform stage ⓘ
hasHyperparameter	cardinality ⓘ depth ⓘ width ⓘ
hasKeyIdea	cardinality as a dimension of network design ⓘ
hasVariant	ResNeXt self-linksurface differs ⓘ surface form: ResNeXt-101 ResNeXt self-linksurface differs ⓘ surface form: ResNeXt-152 ResNeXt self-linksurface differs ⓘ surface form: ResNeXt-50
implementedIn	MXNet ⓘ PyTorch ⓘ TensorFlow ⓘ
influenced	later grouped-convolution architectures ⓘ
introducedInPaper	Aggregated Residual Transformations for Deep Neural Networks ⓘ
optimizationMethod	stochastic gradient descent ⓘ
outperforms	ResNet ⓘ surface form: ResNet on ImageNet classification
paperAuthors	Kaiming He ⓘ Piotr Dollár ⓘ Ross Girshick ⓘ Saining Xie ⓘ Zhuowen Tu ⓘ
publishedBy	Meta AI ⓘ surface form: Facebook AI Research
relatedTo	Inception architecture ⓘ ResNet ⓘ
uses	bottleneck blocks ⓘ grouped convolutions ⓘ split-transform-merge strategy ⓘ

Referenced by (6)

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

ResNet → hasVariant → ResNeXt ⓘ

Xiangyu Zhang → knownFor → ResNeXt ⓘ

this entity surface form: ResNeXt architecture

Xiangyu Zhang → notableWork → ResNeXt ⓘ

this entity surface form: ResNeXt: Aggregated Residual Transformations for Deep Neural Networks

ResNeXt → hasVariant → ResNeXt self-linksurface differs ⓘ

this entity surface form: ResNeXt-50

ResNeXt → hasVariant → ResNeXt self-linksurface differs ⓘ

this entity surface form: ResNeXt-101

ResNeXt → hasVariant → ResNeXt self-linksurface differs ⓘ

this entity surface form: ResNeXt-152