STaDA applies neural style transfer as a data augmentation method for image classification, reporting up to 2% accuracy improvement on Caltech 101 with VGG16, though the effect varies strongly by style.
Content Aware Neural Style Transfer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper presents a content-aware style transfer algorithm for paintings and photos of similar content using pre-trained neural network, obtaining better results than the previous work. In addition, the numerical experiments show that the style pattern and the content information is not completely separated by neural network.
fields
cs.CV 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
STaDA: Style Transfer as Data Augmentation
STaDA applies neural style transfer as a data augmentation method for image classification, reporting up to 2% accuracy improvement on Caltech 101 with VGG16, though the effect varies strongly by style.