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.

Convolutional Neural Networks; Transfer Learning

1. Adewale, S.A., Alenoghena, R. O., Japinye, A. O., Imohi, G. D., & Oluwadamilare, J. O. (2025). The Impact of Foreign Direct Investment in Africa’s Economic Growth: The Mediating Role of Financial Development, International Journal of Research in Social Science and Humanities (IJRSS), 6 (12), 1–21. https://doi.org/10.47505/IJRSS.2025.12.1. [Google Scholar] [Crossref]

2. Alenoghena, R. O., Adebisi, S. D., Osunlana, K. I., & Ifarajimi, G. D. (2026). Assessing the role of globalization and technology adoption in the economic growth of African countries. Quality & Quantity, 1-21. https://doi.org/10.1007/s11135-026-02624-1 [Google Scholar] [Crossref]

3. Ghafouri, S. (2024). *Enhancing image classification accuracy using convolutional neural networks on CIFAR-10 dataset*. University of Victoria. https://hdl.handle.net/1828/20380 [Google Scholar] [Crossref]

4. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press. [Google Scholar] [Crossref]

5. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778. [Google Scholar] [Crossref]

6. Japinye, A. O., Opara, K. O., Alenoghena, R. O., Imohi, G. D., & Oguntade, A. F. (2025). Exploring the Contributions of Human Capital Development to Food Security in African Countries: The Mediating Influence of Technology Adoption. International Journal of Innovative Science and Research Technology, 10(8), 1082-1094. [Google Scholar] [Crossref]

7. Krizhevsky, A. (2009). Learning multiple layers of features from tiny images. University of Toronto. [Google Scholar] [Crossref]

8. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25, 1097–1105. [Google Scholar] [Crossref]

9. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. [Google Scholar] [Crossref]

10. Oluwadamilare, J. O., Alenoghena, R. O., Mariam, J., Sadiq, F. O. A., & Osunlana, K. I. (2025). Intelligent and Secure Digital Technologies: Artificial Intelligence, Internet of Things, and Information Management for Industrial Transformation. International Journal of Humanities Social Science and Management (IJHSSM), 5(6), 188-192. [Google Scholar] [Crossref]

11. Oluwadamilare, J. O., Alenoghena, R. O., Ajaegbu, N. G., Oguntade, F. A., Osunlana,, K. I., & Ajisafe, H. B. (2026). Project Charter Development and Its Influence on Software Project Success. International Journal of Humanities Social Science and Management (IJHSSM), 6(2), 403-409, [Google Scholar] [Crossref]

12. Pandit, S., & Kumar, S. (2020). Improvement in convolutional neural network for CIFAR-10 dataset image classification. International Journal of Computer Applications, 176(37), 25–29. https://doi.org/10.5120/ijca2020920489 [Google Scholar] [Crossref]

13. Prathivi, R. (2020). The optimization of the convolutional neural network transfer learning model for CIFAR-10 image classification. Jurnal RESTI, 4(4). https://doi.org/10.29207/resti.v4i4.2131 [Google Scholar] [Crossref]

14. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4510–4520. [Google Scholar] [Crossref]

15. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. [Google Scholar] [Crossref]

16. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1–9. [Google Scholar] [Crossref]

17. Vinay, S. B., & Balasubramanian, S. (2023). A comparative study of convolutional neural networks and cybernetic approaches on CIFAR-10 dataset. International Journal of Machine Learning and Cybernetics, 1(1), 1–12. https://doi.org/10.17605/OSF.IO/QY32B [Google Scholar] [Crossref]

18. Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., & Tang, X. (2017). Residual attention network for image classification. arXiv preprint arXiv:1704.06904. [Google Scholar] [Crossref]

• The Role of Artificial Intelligence in Revolutionizing Library Services in Nairobi: Ethical Implications and Future Trends in User Interaction
• ESPYREAL: A Mobile Based Multi-Currency Identifier for Visually Impaired Individuals Using Convolutional Neural Network
• Comparative Analysis of AI-Driven IoT-Based Smart Agriculture Platforms with Blockchain-Enabled Marketplaces
• AI-Based Dish Recommender System for Reducing Fruit Waste through Spoilage Detection and Ripeness Assessment
• SEA-TALK: An AI-Powered Voice Translator and Southeast Asian Dialects Recognition