EnsembleDRM Model for Multiclass Image Classification in Deep Learning

Abstract

Convolutional neural networks (CNNs) have performed exceptionally well in various computer vision tasks. Previously, researchers relied on feature extraction and then classification. With CNNs, feature extraction and classification are performed in a single step. Therefore, incorporating a set of convolutional neural networks, known as an ensemble, can help increase the effectiveness of their behavior. This paper presents an architecture that is the result of collaborative efforts, consisting of three types of CNN: Densenet121, Resnet101, and MobileNetV2. We also present experimental results using the Cifar10 and Cifar100 datasets, achieving impressive classification accuracy of 99% for Cifar10 and 86% for Cifar100. This case study contributes to deep learning optimization and benefits researchers and practitioners looking for optimal approaches in various computer vision applications. We also evaluate the scalability and robustness of our proposed method in the context of different CNN structures by using more than one model.