Improving Image Recognition with Limited Data via WACGAN-GP-Based Data Augmentation
Source abstract
Abstract
With the rapid advancement of deep learning, data acquisition remains a persistent challenge, as model effectiveness heavily relies on the quality and quantity of training data. To address the difficulties of time-consuming and labor-intensive data collection, data augmentation techniques are commonly adopted. In this study, the proposed WACGAN-GP, a Generative Adversarial Network (GAN) architecture, serves as an effective data augmentation tool designed to augment training datasets and bolster model performance. This method integrates the advantages of the Auxiliary Classifier GAN and the Wasserstein GAN with gradient penalty to generate diverse and realistic samples. Experiments were conducted on three image datasets—MNIST, CIFAR-10, and a ship classification dataset—under limited training data conditions. By incorporating WACGAN-GP generated synthetic samples into the original training sets, classification performance was evaluated in both balanced and imbalanced scenarios. The results demonstrate that the proposed GAN-based approach significantly improves recognition accuracy and outperforms conventional augmentation methods, such as horizontal and vertical flipping.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Generative Adversarial Networks and Image Synthesis · Advanced Neural Network Applications · Machine Learning and Data Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Systems and Naval Mechatronic Engineering, National Cheng Kung University, Tainan 701, Taiwan
Funding
National Science and Technology Council, Taiwan
References (35)
Show source-provided references
1. A Review of Artificial Intelligence (AI) in Education from 2010 to 202010.1155/2021/8812542 ↗
2. Deep learning10.1038/nature14539 ↗
3. Oquab, M., Bottou, L., Laptev, I., and Sivic, J. (2014, January 24–27). Learning and transferring mid-level image representations using convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.222 ↗
4. Rajvanshi, S., Kaur, G., Dhatwalia, A., Singla, A., and Bhasin, A. (2023, January 14–15). Research on problems and solutions of overfitting in machine learning. Proceedings of the International Conference on Artificial-Business Analytics, Quantum and Machine Learning, Faridabad, India.10.1007/978-981-97-2508-3_47 ↗
5. Sun, C., Shrivastava, A., Singh, S., and Gupta, A. (2017, January 22–29). Revisiting unreasonable effectiveness of data in deep learning era. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.97 ↗
6. A survey on deep learning in medical image analysis10.1016/j.media.2017.07.005 ↗
7. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
8. On data augmentation for GAN training10.1109/TIP.2021.3049346 ↗
9. Arjovsky, M., and Bottou, L. (2017). Towards principled methods for training generative adversarial networks. arXiv.
10. Addressing the class imbalance problem in medical datasets10.7763/IJMLC.2013.V3.307 ↗
11. Zhu, W., Shi, Z., and Ying, W. (2023, January 18–22). SAR Image Classification of Vessel Based on Data Augmentation and Deep Learning. Proceedings of the 2023 IEEE 18th Conference on Industrial Electronics and Applications (ICIEA), Ningbo, China.10.1109/ICIEA58696.2023.10241440 ↗
12. Mikołajczyk, A., and Grochowski, M. (2018, January 9–12). Data augmentation for improving deep learning in image classification problem. Proceedings of the 2018 international interdisciplinary PhD workshop (IIPhDW), Swinoujscie, Poland.10.1109/IIPHDW.2018.8388338 ↗
13. SMOTE: Synthetic minority over-sampling technique10.1613/jair.953 ↗
14. Zhang, H., Cisse, M., Dauphin, Y.N., and Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. arXiv.10.1007/978-1-4899-7687-1_79 ↗
15. Cubuk, E.D., Zoph, B., Shlens, J., and Le, Q.V. (2020, January 14–19). Randaugment: Practical automated data augmentation with a reduced search space. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA.10.1109/CVPRW50498.2020.00359 ↗
16. Denoising diffusion probabilistic models
17. Training generative adversarial networks with limited data
18. Hendrycks, D., Mu, N., Cubuk, E.D., Zoph, B., Gilmer, J., and Lakshminarayanan, B. (2019). Augmix: A simple data processing method to improve robustness and uncertainty. arXiv.
19. Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., and Yoo, Y. (2019, January 27–28). Cutmix: Regularization strategy to train strong classifiers with localizable features. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.10.1109/ICCV.2019.00612 ↗
20. Müller, S.G., and Hutter, F. (2021, January 11–17). Trivialaugment: Tuning-free yet state-of-the-art data augmentation. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00081 ↗
21. DeVries, T., and Taylor, G.W. (2017). Dataset augmentation in feature space. arXiv.
22. Differentiable augmentation for data-efficient gan training
23. Antoniou, A., Storkey, A., and Edwards, H. (2017). Data augmentation generative adversarial networks. arXiv.
24. Fruit quality and defect image classification with conditional GAN data augmentation10.1016/j.scienta.2021.110684 ↗
25. Mudavathu, K.D.B., Rao, M.C.S., and Ramana, K. (2018, January 15–16). Auxiliary conditional generative adversarial networks for image data set augmentation. Proceedings of the 2018 3rd International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India.10.1109/ICICT43934.2018.9034368 ↗
26. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
27. Krizhevsky, A. (2025, December 15). Learning Multiple Layers of Features from Tiny Images. Available online: https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf.
28. Comparison of two deep learning methods for ship target recognition with optical remotely sensed data10.1007/s00521-020-05307-6 ↗
29. Xie, Z., Lin, R., Wang, L., Zhang, A., Lin, J., and Tang, X. (2023). Data augmentation and deep neural network classification based on ship radiated noise. Front. Mar. Sci., 10.10.3389/fmars.2023.1113224 ↗
30. Abdulraheem, A., Suleiman, J.T., and Jung, I.Y. (2023). Generative Adversarial Network Models for Augmenting Digit and Character Datasets Embedded in Standard Markings on Ship Bodies. Electronics, 12.10.3390/electronics12173668 ↗
31. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative adversarial nets. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada.
32. Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 6–11). Wasserstein generative adversarial networks. Proceedings of the International Conference on Machine Learning. PMLR, Sydney, Australia.
33. Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A.C. (2017). Improved training of wasserstein gans. arXiv.
34. Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv.
35. Odena, A., Olah, C., and Shlens, J. (2017, January 6–11). Conditional image synthesis with auxiliary classifier GANs. Proceedings of the International Conference on Machine Learning, Sydney, Australia.