Data enhancement method based on cyclic generation adversarial network

Authors

  • Shiling Li
  • Tianhong Wang

DOI:

https://doi.org/10.54097/2oatvge7

Keywords:

GAN, Data Augmentation, Object detection, CycleGAN

Abstract

This study introduces a novel data augmentation technique employing Cycle Generative Adversarial Networks (CycleGAN) to mitigate the challenges posed by the paucity of image datasets in deep learning domains. Through the adept training of a CycleGAN model, this method substantially enriches image datasets, thereby enhancing the efficiency of deep learning models in target detection tasks. Distinct from conventional approaches, our strategy incorporates advanced activation functions, relative discriminators, and residual connections, which collectively foster greater image diversity and mitigate mode collapse, all while maintaining a low computational overhead. Evaluations conducted on diverse datasets, including MNIST, Synthetic Aperture Radar (SAR), and medical blood cell images, demonstrate the method's superior augmentation capabilities compared to traditional Deep Convolutional GAN (DCGAN) techniques, underscoring its efficacy and potential utility in preprocessing for deep learning applications.

References

Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A.C., & Bengio, Y. (2014). Generative Adversarial Nets. Neural Information Processing Systems.

Chen Guowei, Liu Lei, Guo Jiayi, Pan Zongxu, Hu Wenlong. Semi-supervised aircraft detection in remote sensing images based on generative adversarial networks [J]. Journal of University of Chinese Academy of Sciences, 2020, 37(4): 539-546.Han B-G, Lee JT, Lim K-T, Choi D-H. License Plate Image Generation using Generative Adversarial Networks for End-To-End License Plate Character Recognition from a Small Set of Real Images. Applied Sciences. 2020; 10(8):2780.

Zhang Gui-mei, LONG Bang-yao, LU Fei-fei. Zero-shot text recognition combined with transfer guidance and bidirectional recurrent structure GAN [J]. Pattern Recognition and Artificial Intelligence, 2020, 33(12): 1083-1096. ZHANG Guimei, LONG Bangyao, LU Feifei. Zero-Shot Text Recognition Combining Transfer Guide and Bidirectional Cycle Structure GAN. , 2020, 33(12): 1083-1096.

MIN Rui, Yang Xuezhi, DONG Zhangyu, et al. SAR image super-resolution reconstruction based on structure enhanced generative adversarial network [J]. Geography and Geo-Information Science, 2021, 37(2):47-53.

Molahasani Majdabadi, M., Ko, SB. Capsule GAN for robust face super resolution. Multimed Tools Appl 79, 31205–31218 (2020).

X. Mao, Q. Li, H. Xie, R. Y. K. Lau, Z. Wang and S. P. Smolley, "Least Squares Generative Adversarial Networks," 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017, pp. 2813-2821, doi: 10.1109/ICCV.2017.304. keywords: {Gallium nitride; Generators; Stability analysis; Entropy; Linear programming;Image resolution},

Zhu Y, Jiang B, Jin H, Zhang M, Gao F, Huang J, Lin T and Wang X. (2024). Networked Time-series Prediction with Incomplete Data via Generative Adversarial Network. ACM Transactions on Knowledge Discovery from Data. 18:5. (1-25). Online publication date: 30-Jun-2024.

Miyato, Takeru, Toshiki Kataoka, Masanori Koyama and Yuichi Yoshida. “Spectral Normalization for Generative Adversarial Networks.” ArXiv abs/1802.05957 (2018): n. pag.

Radford, Alec, Luke Metz and Soumith Chintala. “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks.” CoRR abs / 1511.06434 (2015): n. pag.

Anicet Zanini R, Luna Colombini E. Parkinson's Disease EMG Data Augmentation and Simulation with DCGANs and Style Transfer. Sensors (Basel). 2020 May 3;20(9):2605. doi: 10.3390/s20092605. PMID: 32375217; PMCID: PMC7248755.

Zhu, Jun-Yan, Taesung Park, Phillip Isola and Alexei A. Efros. “Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks.” 2017 IEEE International Conference on Computer Vision (ICCV) (2017): 2242-2251.

Jaderberg, Max, Karen Simonyan, Andrew Zisserman and Koray Kavukcuoglu. “Spatial Transformer Networks.” ArXiv abs/1506.02025 (2015): n. pag.

Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2017. ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 6 (June 2017), 84–90.

Neelakantan, Arvind, Luke Vilnis, Quoc V. Le, Ilya Sutskever, Lukasz Kaiser, Karol Kurach and James Martens. “Adding Gradient Noise Improves Learning for Very Deep Networks.” ArXiv abs/1511.06807 (2015): n. pag.

Downloads

Published

30-03-2024

Issue

Section

Articles

How to Cite

Li, S., & Wang, T. (2024). Data enhancement method based on cyclic generation adversarial network. Journal of Computing and Electronic Information Management, 12(2), 70-75. https://doi.org/10.54097/2oatvge7

Similar Articles

1-10 of 81

You may also start an advanced similarity search for this article.