Abstract | ||
---|---|---|
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 opti... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1049/iet-ipr.2018.5616 | IET Image Processing |
Keywords | Field | DocType |
learning (artificial intelligence),neural nets,pattern classification | Convergence (routing),MNIST database,Pattern recognition,Reference model,Generalization,Latent variable model,Artificial intelligence,Artificial neural network,Mathematics | Journal |
Volume | Issue | ISSN |
13 | 3 | 1751-9659 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chunsheng Guo | 1 | 7 | 4.59 |
Ruizhe Li | 2 | 0 | 0.34 |
Meng Yang | 3 | 1028 | 55.17 |
Xianghong Tang | 4 | 0 | 1.01 |