Advertisement

Sample Generation Combining Generative Adversarial Networks and Residual Dense Networks

  • Ji ChenEmail author
  • Wei Du
  • Xing Wang
  • Haitao Chen
  • Nannan Tang
  • Zhijia Shen
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1075)

Abstract

Recently, the generation of adversarial networks has made great progress in image generation and image enhancement, and it is even able to generate high-quality false images to deceive the human eyes, but Generative Adversarial Networks (GANs) still have problems, such as training process instability and mode collapse. To solve the problems above, we use the dense residual network and the residual networks to construct a generator and a discriminator of the networks Combing the Generative Adversarial Networks and Residual Dense Networks (RDGAN), respectively, and use the spectrum normalization model to constrain the GAN networks which can prevent the parameter size. To avoid gradient anomaly, combining with the TTUR optimization strategy, we design and implement several simulation experiments on the 102 Category Flower Dataset. Experimental results show that our method is superior to most existing methods in most cases.

Keywords

Generative Adversarial Networks Residual Dense Networks Adversarial training RDGAN FID 

Notes

Acknowledgment

The work is supported by National Natural Science Foundation of China (61402212), Program for Liaoning Excellent Talents in University (LJQ2015045), Natural Science Foundation of Liaoning Province (2015020098), and China Postdoctoral Science Foundation (2016M591452).

References

  1. 1.
    Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. In: International Conference on Neural Information Processing Systems, pp. 2672–2680. Curran Associates, Montreal (2014)Google Scholar
  2. 2.
    Mirza, M., Osindero, S.: Conditional generative adversarial nets. Comput. Sci. 2672–2680 (2014)Google Scholar
  3. 3.
    Salimans, T., Goodfellow, I., Zaremba, W., et al.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, Barcelona, pp. 2234–2242 (2016)Google Scholar
  4. 4.
    Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: International Conference on Learning Representations, San Juan, Puerto Rico (2016). J. Mach. Learn. Res. (2016)Google Scholar
  5. 5.
    Zhao, J., Mathieu, M., LeCun, Y.: Energy-based generative adversarial network (2016). arXiv preprint arXiv:1609.03126
  6. 6.
    Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN (2017). arXiv preprint: arXiv:1701.07875
  7. 7.
    Mao, X., Li, Q., Xie, H., et al.: Least squares generative adversarial networks. In: The IEEE International Conference on Computer Vision, Honolulu, pp. 2794–2802 (2017)Google Scholar
  8. 8.
    Ledig, C., Theis, L., Huszár, F., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: The IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, pp. 105–114 (2017)Google Scholar
  9. 9.
    Zhang, H., Patel, V.M.: Densely connected pyramid dehazing network. In: The IEEE Conference on Computer Vision and Pattern Recognition, Calvin L. Rampton Salt, pp. 3194–3203 (2018)Google Scholar
  10. 10.
    He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, pp. 770–778 (2016)Google Scholar
  11. 11.
    Huang, G., Liu, Z., Van Der Maaten, L., et al.: Densely connected convolutional networks. In: The IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, pp. 4700–4708 (2017)Google Scholar
  12. 12.
    Zhang, Y., Tian, Y., Kong, Y., et al.: Residual dense network for image super-resolution. In: The IEEE Conference on Computer Vision and Pattern Recognition, Calvin L. Rampton Salt, pp. 2472–2481 (2018)Google Scholar
  13. 13.
    Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. In: The 6th International Conference on Learning Representations Palace Convention Center, Vancouver (2018)Google Scholar
  14. 14.
    Zhang, H., Goodfellow, I., Metaxas, D., et al.: Self-attention generative adversarial networks (2018). arXiv preprint: arXiv:1805.08318
  15. 15.
  16. 16.
    Mao, X., Li, Q., Xie, H., et al.: Least squares generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision 2017, Venice, pp. 2813–2821. IEEE (2017)Google Scholar
  17. 17.
    Berthelot, D., Schumm, T., Metz, L.: BEGAN: boundary equilibrium generative adversarial networks (2017). arXiv:1703.10717
  18. 18.
    Lucic, M., Kurach, K., Michalski, M., et al.: Are GANs created equal? A large-scale study. In: Proceedings of the Advances in Neural Information Processing Systems, Montreal, pp. 697–706. MIT Press (2018)Google Scholar
  19. 19.
    Xia, X., Xu, C., Nan, B.: Inception-v3 for flower classification. In: Proceedings of the International Conference on Image, Vision and Computing, Chengdu, pp. 783–787. IEEE (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Ji Chen
    • 1
    Email author
  • Wei Du
    • 1
  • Xing Wang
    • 1
  • Haitao Chen
    • 1
  • Nannan Tang
    • 1
  • Zhijia Shen
    • 1
  1. 1.School of Electronic and Information EngineeringLiaoning Technical UniversityHuludaoChina

Personalised recommendations