Title | ||
---|---|---|
Deep variance network: An iterative, improved CNN framework for unbalanced training datasets. |
Abstract | ||
---|---|---|
•We propose a novel deep variance network (DVN) by integrating subspaces with Bayesian network into CNN framework.•We propose a hierarchical Bayesian model for unbalance learning of inner-class heterogeneity and inter-class homogeneity.•We generate virtual samples to complete the unbalanced dataset in a top-down way from feature level to image level. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1016/j.patcog.2018.03.035 | Pattern Recognition |
Keywords | Field | DocType |
Deep variance network,Unbalanced training datasets,Convolutional neural network,Homogeneity,Heterogeneity | Homogeneity (statistics),MNIST database,Bayesian inference,Pattern recognition,Convolutional neural network,Linear subspace,Artificial intelligence,Mathematics,Machine learning | Journal |
Volume | Issue | ISSN |
81 | 1 | 0031-3203 |
Citations | PageRank | References |
2 | 0.40 | 40 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shuai Li | 1 | 175 | 31.37 |
Wenfeng Song | 2 | 9 | 5.22 |
Hong Qin | 3 | 2120 | 184.31 |
Aimin Hao | 4 | 183 | 40.57 |