Advertisement

A New Family of Generative Adversarial Nets Using Heterogeneous Noise to Model Complex Distributions

  • Ancheng Lin
  • Jun Li
  • Lujuan Zhang
  • Lei Shi
  • Zhenyuan Ma
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11320)

Abstract

Generative adversarial nets (GANs) are effective framework for constructing data models and enjoys desirable theoretical justification. On the other hand, realizing GANs for practical complex data distribution often requires careful configuration of the generator, discriminator, objective function and training method and can involve much non-trivial effort.

We propose an novel family of generative adversarial nets (GANs), where we employ both continuous noise and random binary codes in the generating process. The binary codes in the new GAN model (named BGANs) play the role of categorical latent variables helps improve the model capability and training stability when dealing with complex data distributions. BGAN has been evaluated and compared with existing GANs trained with the state-of-the-art method on both synthetic and practical data. The empirical evaluation shows effectiveness of BGAN.

References

  1. 1.
    Breuleux, O., Bengio, Y., Vincent, P.: Unlearning for better mixing. Technical Report 1349, Université de Montréal/DIRO (2010)Google Scholar
  2. 2.
    Breuleux, O., Bengio, Y., Vincent, P.: Quickly generating representative samples from an RBM-derived process. Neural Comput. 23(8), 2058–2073 (2011)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Choi, Y., Choi, M., Kim, M., Ha, J.-W., Kim, S., Choo, J.: Stargan: unified generative adversarial networks for multi-domain image-to-image translation. arXiv preprint arXiv:1711.09020 (2017)
  4. 4.
    Denton, E.L., Chintala, S., Fergus, R., et al.: Deep generative image models using a laplacian pyramid of adversarial networks, pp. 1486–1494 (2015)Google Scholar
  5. 5.
    Garimella, S., Hermansky, H.: Factor analysis of auto-associative neural networks with application in speaker verification. IEEE Trans. Neural Netw. Learn. Syst. 24(4), 522–528 (2013)CrossRefGoogle Scholar
  6. 6.
    Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style. CoRR, abs/1508.06576 (2015)Google Scholar
  7. 7.
    Goodfellow, I.J.: NIPS 2016 tutorial: generative adversarial networks. CoRR, abs/1701.00160 (2017)Google Scholar
  8. 8.
    Goodfellow, I.J., Mirza, M., Courville, A.C., Bengio, Y.: Multi-prediction deep Boltzmann machines. In: NIPS, pp. 548–556 (2013)Google Scholar
  9. 9.
    Goodfellow, I.J., et al.: Generative adversarial networks. CoRR, abs/1406.2661 (2014)Google Scholar
  10. 10.
    Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein gans. In: NIPS, pp. 5769–5779 (2017)Google Scholar
  11. 11.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  12. 12.
    Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Hoang, Q., Nguyen, T.D., Le, T., Phung, D.: MGAN: training generative adversarial nets with multiple generators. In: ICLR, p. 24 (2018)Google Scholar
  14. 14.
    Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR, pp. 1125–1134 (2017)Google Scholar
  15. 15.
    Khosrowabadi, R., Quek, C., Ang, K.K., Wahab, A.: ERNN: a biologically inspired feedforward neural network to discriminate emotion from EEG signal. IEEE Trans. Neural Netw. Learn. Syst. 25(3), 609–620 (2014)CrossRefGoogle Scholar
  16. 16.
    Kingma, D.P., Welling, M.: Auto-encoding variational bayes. CoRR, abs/1312.6114 (2013)Google Scholar
  17. 17.
    Krizhevsky, A., Nair, V., Hinton, G.: The CIFAR-10 dataset (2014)Google Scholar
  18. 18.
    LeCun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  19. 19.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  20. 20.
    Liu, M.Y., Breuel, T., Kautz, J.: Unsupervised image-to-image translation networks. In: NIPS, pp. 700–708 (2017)Google Scholar
  21. 21.
    Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_2CrossRefGoogle Scholar
  22. 22.
    Maskin, E.: Nash equilibrium and welfare optimality. Rev. Econ. Stud. 66(1), 23–38 (1999)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Mirza, M., Osindero, S.: Conditional generative adversarial nets. CoRR, abs/1411.1784 (2014)Google Scholar
  24. 24.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML, pp. 807–814 (2010)Google Scholar
  25. 25.
    Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: ICML, pp. 2642–2651 (2017)Google Scholar
  26. 26.
    Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. CoRR, abs/1511.06434 (2015)Google Scholar
  27. 27.
    Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: ICML, pp. 1060–1069 (2016)Google Scholar
  28. 28.
    Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91–99 (2015)Google Scholar
  29. 29.
    Schwarz, B., Richardson, M.: Using a de-convolution window for operating modal analysis. In: Proceedings of the IMAC. Citeseer (2007)Google Scholar
  30. 30.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556 (2014)Google Scholar
  31. 31.
    Song, J., He, T., Gao, L., Xu, X., Hanjalic, A., Shen, H.T.: Binary generative adversarial networks for image retrieval. In: AAAI (2018)Google Scholar
  32. 32.
    Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  33. 33.
    Sutskever, I., Hinton, G.E., Taylor, G.W.: The recurrent temporal restricted Boltzmann machine. In: NIPS, pp. 1601–1608 (2008)Google Scholar
  34. 34.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS, pp. 3104–3112 (2014)Google Scholar
  35. 35.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI, pp. 4278–4284 (2017)Google Scholar
  36. 36.
    Cortes, C., LeCun, Y., Burges, C.J.C.: The MNIST database of handwritten digits (1998)Google Scholar
  37. 37.
    Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Ancheng Lin
    • 1
  • Jun Li
    • 2
  • Lujuan Zhang
    • 3
  • Lei Shi
    • 4
    • 5
  • Zhenyuan Ma
    • 3
  1. 1.School of Computer SciencesGuangdong Polytechnic Normal UniversityGuangzhouChina
  2. 2.School of Software and Centre for Artificial Intelligence, Faculty of Engineering and Information TechnologyUniversity of Technology SydneySydneyAustralia
  3. 3.School of Mathematics and System SciencesGuangdong Polytechnic Normal UniversityGuangzhouChina
  4. 4.National Education Examinations Authority Ministry of Education of ChinaBeijingChina
  5. 5.School of Information Resource ManagementRenmin University of ChinaBeijingChina

Personalised recommendations