Ensemble learning in CNN augmented with fully connected subnetworks

Convolutional Neural Networks (CNNs) [1] are attracting a great deal of attention because they show remarkable performance in general object recognition tasks. Various methods have been proposed so far for improving the performance of CNNs: pre-processing [2-4], dropout [5], batch normalization [6], ensemble learning [7, 8], and so on. In this paper, we propose a new model based on CNNs to further improve the performance in image recognitioin tasks. Our model consists of one base CNN and multiple Fully Connected SubNetworks (FCSNs). The base CNN generates a set of multi-channel feature-maps after each convolutional layer. The set of feature-maps generated by the last convolutional layer is divided along channels into disjoint subsets, and each subset is assigned to one of the FCSNs, which is trained independent of others so that it can predict the class label from the subset of the featuremaps assigned to it.