Inception v2

E472888

Inception architecture variant convolutional neural network architecture deep learning model architecture

Inception v2 is an improved version of Google’s Inception convolutional neural network architecture that enhances accuracy and efficiency through refined module design and training techniques.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (1)

Label	Occurrences
Inception v2 canonical	1

Statements (35)

Predicate	Object
instanceOf	Inception architecture variant ⓘ convolutional neural network architecture ⓘ deep learning model architecture ⓘ
applicationDomain	object recognition ⓘ visual feature extraction ⓘ
architectureType	multi-branch convolutional network ⓘ
basedOn	Inception v1 NERFINISHED ⓘ
characteristic	enhanced regularization through batch normalization ⓘ more efficient use of parameters ⓘ refined Inception module structure ⓘ
designedFor	image classification ⓘ large-scale visual recognition ⓘ
developedBy	Google NERFINISHED ⓘ Google Research NERFINISHED ⓘ
field	computer vision ⓘ deep learning ⓘ machine learning ⓘ
goal	improve accuracy ⓘ improve computational efficiency ⓘ improve training stability ⓘ reduce computational cost ⓘ
improvesUpon	Inception v1 module design ⓘ training techniques of earlier Inception models ⓘ
optimizationTarget	accuracy–efficiency trade-off ⓘ
partOf	Inception family of architectures NERFINISHED ⓘ
relatedTo	GoogLeNet NERFINISHED ⓘ Inception v3 NERFINISHED ⓘ
typicalInput	RGB images ⓘ
usedIn	image recognition benchmarks ⓘ
usedWith	data augmentation techniques ⓘ stochastic gradient descent ⓘ
uses	Inception modules ⓘ batch normalization ⓘ convolutional layers ⓘ factorized convolutions ⓘ

Referenced by (1)

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

Inception architecture → hasVariant → Inception v2 ⓘ