A Comparative Study of Deep Learning Models for Image Classification: Simple MLP, Deep MLP, Basic CNN, LeNet CNN

A Comparative Study of Deep Learning Architectures for Image Classification

Image classification is a major area in computer vision, driven by rapid advances in deep learning. Over the last decade, convolutional neural networks (CNNs) and their variants have achieved high performance in applications such as medical diagnosis, autonomous driving, industrial inspection, remote sensing, and biometrics. However, choosing the right model remains challenging due to trade-offs between accuracy, computational cost, efficiency, and robustness. This paper presents a comparative study of different deep learning architectures, including classical CNNs, deep hierarchical models, residual and dense networks, and compound-scaled architectures. Using a common evaluation framework and standard datasets, the study analyzes performance based on key design factors such as depth, width, receptive field, skip connections, and normalization. Theoretical concepts like convolution operations, residual learning, and optimization are also discussed.The results show that deeper networks provide better representation, while residual connections and compound scaling improve training stability and efficiency. Lightweight models perform well in resource-limited and real-time environments. Overall, the study offers practical guidance for selecting suitable architectures and highlights future research areas such as neural architecture search, self-supervised learning, and efficient model deployment.

A Comparative Study of Optimization Algorithms, Regularization Techniques, and CNN Architectures for CIFAR-10 Image Classification

In this paper, we perform a systematic empirical study of deep learning techniques on the CIFAR-10 image classification benchmark. We study three inter-related aspects of neural network design: (1) the relative impact of nine gradient descent optimisation algorithms on a baseline Multi-Layer Perceptron (MLP); (2) the effectiveness of six regularisation techniques namely; L2 weight decay, Dropout, Data Augmentation, Gaussian Noise Injection, Early Stopping, and Ensemble Learning; on model generalisation; and (3) a benchmark comparison of five landmark Convolutional Neural Network (CNN) architectures alongside Inception V3 trained from scratch. We also investigate autoencoder-based image reconstruction and a side-by-side comparison of linear Principal Component Analysis (PCA) with non-linear autoencoder representations. Nesterov Accelerated Gradient achieves the lowest training loss (1.5814) in short-run experiments. VGGNet achieves the highest test accuracy (75.09%) among CNN architectures trained from scratch for five epochs. Early Stopping yields the best regularisation outcome, and non-linear autoencoders outperform PCA in reconstruction quality. All experiments use TensorFlow 2.x and Keras on CIFAR-10.

Comparative Analysis of Custom and Pre-Trained Convolutional Neural Networks (CNNs) for Object Recognition on the Cifar-10 Dataset

Convolutional Neural Networks (CNNs) have significantly changed image classification over the years by allowing computers to learn features directly from raw pixel data. However, deciding between building a customised model and using a pre-trained one can be a difficult task, especially when working with small datasets. In this study, we compare a custom CNN with three pre-trained models—VGG16, ResNet50, and MobileNetV2—on the CIFAR-10 dataset, which comprises 60,000 colour images (32×32 pixels) across 10 categories. We measured model performance using accuracy, precision, recall, F1-score, and training time. The results show that pre-trained models performed much better than the customised model. ResNet50 had the highest accuracy at 92.4%. However, MobileNetV2 gave the best mix of speed (1,800 seconds to train) and accuracy (90.2%). The custom CNN reached 82.3% accuracy, used less memory, and did not need image resizing. These results offer clear benchmarks for choosing models in the face of limited resources. They also demonstrate that transfer learning can achieve strong performance, while showing that custom CNNs remain useful for learning and simple tasks.

Enhancing image classification accuracy with AL-CNN: a hybrid of AlexNet and LeNet architectures

Image classification is a key application of computer vision with direct relevance to medical diagnostics, autonomous vehicles, and remote sensing. This paper discusses the use of an adaptive learning convolutional neural network (AL-CNN) for image classification, with results reported on a large-scale benchmark dataset that is widely accepted for performance evaluation. The AL-CNN architecture integrates convolutional, pooling, and fully connected layers. The model was systematically trained on a subset of the dataset and subsequently tested on an independent validation subset to evaluate its efficiency and generalization capability. In addition, optimization techniques such as data augmentation, dropout, and advanced activation functions were employed to further enhance model performance. The results, based on accuracy metrics, indicate the successful implementation of the proposed AL-CNN model for reliable and accurate image classification. This study demonstrates the potential of the AL-CNN approach to address various complexities in image classification, thereby enabling further innovation in this domain.

Performance Comparison of ALEXNET, VGG16, and ResNet on CIFAR‑10 Image Classification

Landscape Image Classification Using Convolutional Neural Network on Intel Image Classification Datase

A lightweight CNN architecture that achieves competitive performance without relying on pretrained models or transfer learning approaches, making it suitable for deployment on resource-constrained devices and balanced classification performance across all classes is developed.