No Detail Found!

Performance Analysis of ResNet50 on Balanced and Imbalanced Image Classification Datasets

Author(s)
Kainat Irfan Department of Computer Science, University of Management and Technology, Sialkot 51310, Pakistan
Mujeeb-Ur-Rehman Department of Computer Science, University of Management and Technology, Sialkot 51310, Pakistan
Abstract
This study explores the performance of a well-known deep learning model ResNet50 on CIFAR-10 and Fashion-MNIST datasets. ResNet50 is an efficient and scalable model for image classification. The model is evaluated on both datasets under balanced and imbalanced conditions. We trained the model using different train-test splits, fine-tuned hyperparameters and applied regularization techniques L1, L2 and dropout. The model is evaluated using Accuracy, Precision, Recall, F1-score, ROC-AUC, Training and Testing time and Memory usage. The results demonstrate that the model performs better on the Fashion-MNIST dataset (86% accuracy) compared to CIFAR-10 dataset (73% accuracy) across all settings. Additionally, the performance of both datasets is better in imbalanced settings but demands more computational resources. These results emphasize how crucial dataset balancing and hyperparameter tuning are to the real-world optimization of deep learning models.
Publication Details
Page(s) 16-29
DOI DOI not available
Published Journal: The Sciencetech, Volume: 6, Issue: 2, Year: 2025

Request the full text from PASTIC

Keywords
Fashion-MNIST, deep learning, ResNet50, Image Classification, Cifar-10, Class Imbalance
References
Alam M. Z. .2024 .Enhancing Transfer Learning for Medical Image Classification with SMOTE: A Comparative Study. arXiv preprint arXiv:2412, : 20235.
Bello I. F. .2021 .Revisiting resnets: Improved training and scaling strategies. Advances in Neural Information Processing Systems, 34 : 22614-22627.
Buda M. M. .2018 .A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks, 106 : 249-259.
He K. Z. .2016 .Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), : 770-778.
Hossain M. B. .2022 .Transfer learning with fine-tuned deep CNN ResNet50 model for classifying COVID-19 from chest X-ray images. Informatics in Medicine Unlocked, 30 : 100916.
Howard A. G. .2017 .Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:, 1704 : 04861.
Huang G. L. .2017 .Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, : 4700-4708.
Johnson J. M. .2019 .Survey on deep learning with class imbalance. Journal of Big Data, 6(1) : 1-54.
Krizhevsky A. .2009 .Learning multiple layers of features from tiny images. , : .
Lin T. Y. .2017 .Focal loss for dense object detection.. In Proceedings of the IEEE international conference on computer vision, : 2980-2988.
Ojo M. O. .2023 .Improving Deep Learning Classifiers Performance via Preprocessing and Class Imbalance Approaches in a Plant Disease Detection Pipeline. , 13(3) : 887.
O'Mahony N. C. .2020 .Deep learning vs. traditional computer vision. proceedings of the 2019 computer vision conference (CVC), : 128-144.
Panigrahi U. S. .2024 .A ResNet-101 deep learning framework induced transfer learning strategy for moving object detection. Image and Vision Computing, 146 : 105021.
Shwartz-Ziv R. G. .2023 .Simplifying neural network training under class imbalance. Advances in Neural Information Processing Systems, 36 : 35218-35245.
Simonyan K. .2014 .Very deep convolutional networks for largescale image recognition. , 1409 : 1556.
Tan M. .2019 .Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, : 6105-6114.
Wang G. L. .2022 .A network combining a transformer and a convolutional neural network for remote sensing image change detection. Remote Sensing, 14(9) : 2228.
Xiao H. R. .2017 .Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:, 1708 : 07747.
0

Citations

0

Downloads

6

Views