No Access

School of Information Technology and Engineering, Tianjin University of Technology and Education, No. 1310, Dagu South Road, Jinnan District, Tianjin, P. R. China

Dunhuang Shi

https://orcid.org/0009-0007-1176-2560

School of Information Technology and Engineering, Tianjin University of Technology and Education, No. 1310, Dagu South Road, Jinnan District, Tianjin, P. R. China

E-mail Address: 1686840207@qq.com

Search for more papers by this author

, and

Qi Pan

https://orcid.org/0000-0002-7924-3173

School of Information Technology and Engineering, Tianjin University of Technology and Education, No. 1310, Dagu South Road, Jinnan District, Tianjin, P. R. China

E-mail Address: 1441675261@qq.com

Search for more papers by this author

https://doi.org/10.1142/S1469026824500214Cited by:1 (Source: Crossref)

Abstract

In the research of deep learning, an Unsupervised deep convolution-generated Generated Adversarial Network (UGAN) usually needs a large number of data samples to train. However, when faced with some small samples, the performance of the algorithm is often degraded due to over-fitting. Combined with specially designed data enhancement methods, a generated adversarial network optimization algorithm based on adaptive data augmentation (AdauGAN) is proposed. The adaptive data augmentation module is added before the discriminant network, and a spatial transformation is carried out simultaneously at the probability distribution level of generated data and real data. To alleviate the over-fitting phenomenon in the training process, the current enhancement intensity is adjusted adaptively after the over-fitting occurs. The proposed algorithm is verified on SVHN, CelebA and CIFAR-10 data sets. The Frechet Inception Distance (FID) values of AdauGAN achieve 22.10, 23.94, 34.87, respectively, which is close to or even higher than the training results of Deep Convolution Generated Adversarial Network (DCGAN) under all data. Extensive experiment results show that the proposed Adaugan has an excellent performance in small samples. Besides, in some cases, it can catch up with the large sample results of existing algorithms.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

1. H. Panwar et al., Application of deep learning for fast detection of COVID-19 in X-rays using nCOVnet, Chaos Solit. Fractals 138 (2020) 109944. Crossref, Google Scholar
2. Y. Oh, S. Park and Y. C. Ye, Deep learning covid-19 features on cxr using limited training data sets, IEEE Trans. Med. Imaging 39(8) (2020) 2688–2700. Crossref, Google Scholar
3. B. Xiao, Y. Liu and B. Xiao, Accurate state-of-charge estimation approach for lithium-ion batteries by gated recurrent unit with ensemble optimizer, IEEE Access 7 (2019) 54192–54202. Crossref, Google Scholar
4. F. Xiao et al., State of charge estimation for lithium-ion battery based on Gaussian process regression with deep recurrent kernel, Int. J. Electr. Power Energy Syst. 124 (2021) 106369. Crossref, Google Scholar
5. M. I. Georgescu et al., Anomaly detection in video via self-supervised and multi-task learning, in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, 2021, pp. 12742–12752. Crossref, Google Scholar
6. X. Ma et al., Application of deep learning convolutional neural networks for internal tablet defect detection: High accuracy, throughput, and adaptability, J. Pharm. Sci. 109(4) (2020) 1547–1557. Crossref, Google Scholar
7. M. M. Bejani and M. Ghatee, A systematic review on overfitting control in shallow and deep neural networks, Artif. Intell. Rev. 54(8) (2021) 6391–6438. Crossref, Google Scholar
8. S. Kornblith, J. Shlens and Q. V. Le, Do better imagenet models transfer better? in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, 2019, pp. 2661–2671. Crossref, Google Scholar
9. A. Krizhevsky and G. Hinton, Learning Multiple Layers of Features from Tiny Images (Computer Science University of Toronto, Canada, 2009). Google Scholar
10. Y. Netzer et al., Reading digits in natural images with unsupervised feature learning, (2011). Google Scholar
11. Z. Liu et al., Deep learning face attributes in the wild, in Proc. IEEE Int. Conf. Computer Vision, 2015, pp. 3730–3738. Crossref, Google Scholar
12. G. Kaissis et al., End-to-end privacy preserving deep learning on multi-institutional medical imaging, Nat. Mach. Intell. 3(6) (2021) 473–484. Crossref, Google Scholar
13. X. He et al., Triplet-center loss for multi-view 3d object retrieval, in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2018, pp. 1945–1954. Crossref, Google Scholar
14. E. D. Cubuk et al., Randaugment: Practical automated data augmentation with a reduced search space, in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition Workshops, 2020, pp. 702–703. Crossref, Google Scholar
15. A. Santoro, S. Bartunov, M. Botvinick, D. Wierstra and T. Lillicrap, Meta-learning with memory-augmented neural networks, Proc. Int. Conf. Mach. Learn. (2016), pp. 1842–1850. Google Scholar
16. M. Heusel et al., Gans trained by a two time-scale update rule converge to a local nash equilibrium, Adv. Neural Inf. Process. Syst. (2017) 30. Google Scholar
17. I. Goodfellow et al., Generative adversarial networks, Commun. ACM 63(11) (2020) 139–144. Crossref, Google Scholar
18. A. Radford, L. Metz and S. Chintala, Unsupervised representation learning with deep convolutional generative adversarial networks, preprint (2015), arXiv:1511.06434. Google Scholar
19. Z. Zhong et al., Random erasing data augmentation, in Proc. AAAI Conf. Artificial Intelligence, 2020, pp. 13001–13008. Crossref, Google Scholar
20. S. Mounsaveng et al., Adversarial learning of general transformations for data augmentation, preprint (2019), arXiv:1909.09801. Google Scholar
21. J. H. Lee et al., Smoothmix: A simple yet effective data augmentation to train robust classifiers, in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition Workshops, 2020, pp. 756–757. Crossref, Google Scholar
22. N. T. Tran et al., On data augmentation for GAN training, IEEE Trans. Image Process. 30 (2021) 1882–1897. Crossref, Google Scholar
23. L. Taylor and G. Nitschke, Improving deep learning with generic data augmentation, 2018 IEEE Symp. Series on Computational Intelligence (SSCI), IEEE, 2018, pp. 1542–1547. Crossref, Google Scholar
24. A. Khan and K. Fraz, Post-training iterative hierarchical data augmentation for deep networks, Adv. Neural Inf. Process. Syst. 33 (2020). Google Scholar
25. L. Nanni, G. Maguolo and M. Paci, Data augmentation approaches for improving animal audio classification, Ecol. Inform. 57 (2020) 101084. Crossref, Google Scholar
26. N. A. Farda et al., Sanders classification of calcaneal fractures in CT images with deep learning and differential data augmentation techniques, Injury 52(3) (2021) 616–624. Crossref, Google Scholar
27. Z. Zhao et al., Improved consistency regularization for gans, preprint (2020), arXiv:2002.04724. Google Scholar
28. A. Bora, E. Price and A. G. Dimakis, AmbientGAN: Generative models from lossy measurements, Proc. ICLR 2 (2018) 5. Google Scholar