The Relative Performance of Ensemble Methods with Deep Convolutional Neural Networks for Image Classification
This work addresses the problem of optimizing ensemble methods for image classification, providing insights for researchers and practitioners, but it is incremental as it builds on existing ensemble techniques.
The study investigated the performance of various ensemble methods, including unweighted averaging, majority voting, Bayes Optimal Classifier, and Super Learner, for image classification using deep convolutional neural networks, finding that the Super Learner achieved the best performance across all experiments.
Artificial neural networks have been successfully applied to a variety of machine learning tasks, including image recognition, semantic segmentation, and machine translation. However, few studies fully investigated ensembles of artificial neural networks. In this work, we investigated multiple widely used ensemble methods, including unweighted averaging, majority voting, the Bayes Optimal Classifier, and the (discrete) Super Learner, for image recognition tasks, with deep neural networks as candidate algorithms. We designed several experiments, with the candidate algorithms being the same network structure with different model checkpoints within a single training process, networks with same structure but trained multiple times stochastically, and networks with different structure. In addition, we further studied the over-confidence phenomenon of the neural networks, as well as its impact on the ensemble methods. Across all of our experiments, the Super Learner achieved best performance among all the ensemble methods in this study.