Open AccessDeep neural network with FGL for small dataset classification
Author(s) -
Guo Chunsheng,
Li Ruizhe,
Yang Meng,
Tang Xianghong
Publication year - 2019
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2018.5616
Subject(s) - mnist database , computer science , artificial neural network , artificial intelligence , convergence (economics) , pattern recognition (psychology) , feature (linguistics) , machine learning , contextual image classification , training set , data mining , image (mathematics) , linguistics , philosophy , economics , economic growth
In certain applications, classification models have to be trained with small datasets. This study proposes a new deep neural network with a feature generalisation layer (FGL). First, instead of using a generative network for data augmentation, the FGL is modelled using a latent variable model to diversify features directly by sharing other layers. Then, dual‐objective functions are defined to optimise the parameters of the network: one minimises the generation error and the other minimises the classification error. Finally, a parallel multibranch structure is used in the FGL to improve the convergence of model training. The classification accuracy obtained using various quantities of training samples increased up to 4.63% on the MNIST dataset, up to 3.00% on the CIFAR10 nature image dataset, over the reference model. These experimental results illustrate the effectiveness of the authors’ method for training classification models with small datasets.