IEA: Inner Ensemble Average within a convolutional neural network
Machine Learning
2019-08-08 v5 Machine Learning
Abstract
Ensemble learning is a method of combining multiple trained models to improve model accuracy. We propose the usage of such methods, specifically ensemble average, inside Convolutional Neural Network (CNN) architectures by replacing the single convolutional layers with Inner Average Ensembles (IEA) of multiple convolutional layers. Empirical results on different benchmarking datasets show that CNN models using IEA outperform those with regular convolutional layers. A visual and a similarity score analysis of the features generated from IEA explains why it boosts the model performance.
Cite
@article{arxiv.1808.10350,
title = {IEA: Inner Ensemble Average within a convolutional neural network},
author = {Abduallah Mohamed and Xinrui Hua and Xianda Zhou and Christian Claudel},
journal= {arXiv preprint arXiv:1808.10350},
year = {2019}
}
Comments
Updating results