Enhanced Convolutional Neural Networks for Improved Image Classification

TL;DR

This paper introduces an improved CNN architecture with deeper layers, batch normalization, and dropout, achieving higher accuracy on CIFAR-10 and demonstrating the benefits of architectural enhancements for small-scale image classification.

Contribution

The paper presents a novel CNN architecture that combines deeper convolutional blocks, batch normalization, and dropout to improve classification performance on CIFAR-10.

Findings

Achieved 84.95% test accuracy on CIFAR-10.

Demonstrated the effectiveness of architectural enhancements through ablation studies.

Enhanced CNN outperforms baseline models on small-scale datasets.

Abstract

Image classification is a fundamental task in computer vision with diverse applications, ranging from autonomous systems to medical imaging. The CIFAR-10 dataset is a widely used benchmark to evaluate the performance of classification models on small-scale, multi-class datasets. Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art results; however, they often suffer from overfitting and suboptimal feature representation when applied to challenging datasets like CIFAR-10. In this paper, we propose an enhanced CNN architecture that integrates deeper convolutional blocks, batch normalization, and dropout regularization to achieve superior performance. The proposed model achieves a test accuracy of 84.95%, outperforming baseline CNN architectures. Through detailed ablation studies, we demonstrate the effectiveness of the enhancements and analyze the hierarchical feature representations. This work highlights the potential of refined CNN architectures for tackling small-scale image classification problems effectively.