Ensemble learning in CNN augmented with fully connected subnetworks

Abstract

Convolutional Neural Networks (CNNs) have shown remarkable performance in general object recognition tasks. In this paper, we propose a new model called EnsNet which is composed of one base CNN and multiple Fully Connected SubNetworks (FCSNs). In this model, the set of feature-maps generated by the last convolutional layer in the base CNN is divided along channels into disjoint subsets, and these subsets are assigned to the FCSNs. Each of the FCSNs is trained independent of others so that it can predict the class label from the subset of the feature-maps assigned to it. The output of the overall model is determined by majority vote of the base CNN and the FCSNs. Experimental results using the MNIST, Fashion-MNIST and CIFAR-10 datasets show that the proposed approach further improves the performance of CNNs. In particular, an EnsNet achieves a state-of-the-art error rate of 0.16% on MNIST.

6 pages, 2 figures, 5 tables

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Improved Regularization of Convolutional Neural Networks with Cutout
• AutoAugment: Learning Augmentation Policies from Data
• Training Neural Networks with Local Error Signals
• RMDL: Random Multimodel Deep Learning for Classification
• APAC: Augmented PAttern Classification with Neural Networks

Cited by in corpus (1)

• Single-Qudit Quantum Neural Networks for Multiclass Classification