IEA: Inner Ensemble Average within a convolutional neural network
This work addresses accuracy enhancement in CNNs for computer vision tasks, but it appears incremental as it applies ensemble averaging within existing architectures.
The paper tackled the problem of improving model accuracy in convolutional neural networks by introducing Inner Ensemble Average (IEA) layers to replace single convolutional layers, resulting in CNN models with IEA outperforming regular ones on various benchmarking datasets.
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.