Download pdf
Enhancing Image Classification Performance via GAN-based Data Augmentation
- 1 South China University of Technology, Guangzhou, China
* Author to whom correspondence should be addressed.
Abstract
This paper presents a novel data augmentation strategy that combines GAN-generated samples with optimized sampling to address class imbalance in image classification. Our approach significantly enhances classification accuracy on the CIFAR-10 dataset, achieving a 99.79% accuracy rate—an improvement of 43.57 percentage points over the baseline. Compared to traditional augmentation methods, our strategy better mitigates class imbalance and improves dataset diversity. Further validation on MNIST and STL-10 confirms the generalizability of our method.
Keywords
Data Augmentation, GANClass, Imbalance
[1]. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," in Advances in Neural Information Processing Systems, 2012.
[2]. I. Goodfellow et al., "Generative adversarial nets," in Advances in Neural Information Processing Systems, 2014.
[3]. A. Radford, L. Metz, and S. Chintala, "Unsupervised representation learning with deep convolutional generative adversarial networks," in International Conference on Learning Representations, 2016.
[4]. C. Shorten and T. M. Khoshgoftaar, "A survey on image data augmentation for deep learning," Journal of Big Data, vol. 6, no. 1, pp. 1-48, 2019.
[5]. M. Buda, A. Maki, and M. A. Mazurowski, "A systematic study of the class imbalance problem in convolutional neural networks," Neural Networks, vol. 106, pp. 249-259, 2018.
[6]. I. Goodfellow et al., "Generative adversarial networks," Communications of the ACM, vol. 63, no. 11, pp. 139-144, 2020.
[7]. A. Radford, L. Metz, and S. Chintala, "DCGAN: Deep convolutional generative adversarial networks," arXiv preprint arXiv:1511.06434, 2015.
[8]. M. Frid-Adar et al., "GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification," Neurocomputing, vol. 321, pp. 321-331, 2018.
[9]. M. Mariani, P. R. Ktena, and C. N. Pope, "Balancing datasets using generative adversarial networks," IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 9, pp. 4267-4280, 2021.
[10]. X. Xu, Y. Wang, and X. Ma, "Improving GAN-based data augmentation with diversity-regularized training," IEEE Access, vol. 8, pp. 171089-171099, 2020.
[11]. J. Yang, K. Xu, and Y. Xu, "A review of active learning in the era of deep learning," Pattern Recognition, vol. 110, p. 107123, 2021.
[12]. H. Wang et al., "Training neural networks with optimized data sampling methods," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 6, pp. 2089-2102, 2021.
[13]. T.-Y. Lin et al., "Focal loss for dense object detection," in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2980-2988.
[14]. B. Settles, "Active learning," Synthesis Lectures on Artificial Intelligence and Machine Learning, vol. 6, no. 1, pp. 1-114, 2012.
[15]. X. Chen, Q. Huang, and Z. Zhang, "On the impact of GAN-generated data for imbalanced classification," IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 4, pp. 1356-1367, 2023.
Cite this article
Gao,Z. (2025). Enhancing Image Classification Performance via GAN-based Data Augmentation. Applied and Computational Engineering,151,10-20.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 3rd International Conference on Software Engineering and Machine Learning
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).