Enhanced Convolutional Neural Networks for Improved Image Classification
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909472075546624 |
|---|---|
| author | Yang, Xiaoran Yu, Shuhan Xu, Wenxi |
| author_facet | Yang, Xiaoran Yu, Shuhan Xu, Wenxi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00663 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhanced Convolutional Neural Networks for Improved Image Classification Yang, Xiaoran Yu, Shuhan Xu, Wenxi Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | Enhanced Convolutional Neural Networks for Improved Image Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2502.00663 |