Advertisement

Dist-GAN: An Improved GAN Using Distance Constraints

  • Ngoc-Trung TranEmail author
  • Tuan-Anh Bui
  • Ngai-Man Cheung
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11218)

Abstract

We introduce effective training algorithms for Generative Adversarial Networks (GAN) to alleviate mode collapse and gradient vanishing. In our system, we constrain the generator by an Autoencoder (AE). We propose a formulation to consider the reconstructed samples from AE as “real” samples for the discriminator. This couples the convergence of the AE with that of the discriminator, effectively slowing down the convergence of discriminator and reducing gradient vanishing. Importantly, we propose two novel distance constraints to improve the generator. First, we propose a latent-data distance constraint to enforce compatibility between the latent sample distances and the corresponding data sample distances. We use this constraint to explicitly prevent the generator from mode collapse. Second, we propose a discriminator-score distance constraint to align the distribution of the generated samples with that of the real samples through the discriminator score. We use this constraint to guide the generator to synthesize samples that resemble the real ones. Our proposed GAN using these distance constraints, namely Dist-GAN, can achieve better results than state-of-the-art methods across benchmark datasets: synthetic, MNIST, MNIST-1K, CelebA, CIFAR-10 and STL-10 datasets. Our code is published here (https://github.com/tntrung/gan) for research.

Keywords

Generative Adversarial Networks Image generation Distance constraints Autoencoders 

Notes

Acknowledgement

This work was supported by both ST Electronics and the National Research Foundation(NRF), Prime Minister’s Office, Singapore under Corporate Laboratory @ University Scheme (Programme Title: STEE Infosec - SUTD Corporate Laboratory).

Supplementary material

474202_1_En_23_MOESM1_ESM.pdf (446 kb)
Supplementary material 1 (pdf 446 KB)

References

  1. 1.
  2. 2.
  3. 3.
    Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. arXiv preprint arXiv:1701.04862 (2017)
  4. 4.
    Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICML (2017)Google Scholar
  5. 5.
    Berthelot, D., Schumm, T., Metz, L.: Began: boundary equilibrium generative adversarial networks. arXiv preprint arXiv:1703.10717 (2017)
  6. 6.
    Burda, Y., Grosse, R., Salakhutdinov, R.: Importance weighted autoencoders. arXiv preprint arXiv:1509.00519 (2015)
  7. 7.
    Che, T., Li, Y., Jacob, A.P., Bengio, Y., Li, W.: Mode regularized generative adversarial networks. CoRR (2016)Google Scholar
  8. 8.
    Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Infogan: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2172–2180 (2016)Google Scholar
  9. 9.
    Donahue, J., Krähenbühl, P., Darrell, T.: Adversarial feature learning. arXiv preprint arXiv:1605.09782 (2016)
  10. 10.
    Dumoulin, V., et al.: Adversarially learned inference. arXiv preprint arXiv:1606.00704 (2016)
  11. 11.
    Goodfellow, I.: Nips 2016 tutorial: generative adversarial networks. arXiv preprint arXiv:1701.00160 (2016)
  12. 12.
    Goodfellow, I., et al.: Generative adversarial nets. In: NIPS, pp. 2672–2680 (2014)Google Scholar
  13. 13.
    Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein gans. In: Advances in Neural Information Processing Systems, pp. 5767–5777 (2017)Google Scholar
  14. 14.
    Guo, Y., Cheung, N.M.: Efficient and deep person re-identification using multi-level similarity. In: CVPR (2012)Google Scholar
  15. 15.
    Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANS trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, pp. 6626–6637 (2017)Google Scholar
  16. 16.
    Hoang, T., Do, T.T., Le Tan, D.K., Cheung, N.M.: Selective deep convolutional features for image retrieval. In: Proceedings of the 2017 ACM on Multimedia Conference, pp. 1600–1608. ACM (2017)Google Scholar
  17. 17.
    Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
  18. 18.
    Larsen, A.B.L., Sønderby, S.K., Larochelle, H., Winther, O.: Autoencoding beyond pixels using a learned similarity metric. arXiv preprint arXiv:1512.09300 (2015)
  19. 19.
    Li, C., Alvarez-Melis, D., Xu, K., Jegelka, S., Sra, S.: Distributional adversarial networks. arXiv preprint arXiv:1706.09549 (2017)
  20. 20.
    Lucic, M., Kurach, K., Michalski, M., Gelly, S., Bousquet, O.: Are gans created equal? a large-scale study. CoRR (2017)Google Scholar
  21. 21.
    Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I.: Adversarial autoencoders. In: International Conference on Learning Representations (2016)Google Scholar
  22. 22.
    Metz, L., Poole, B., Pfau, D., Sohl-Dickstein, J.: Unrolled generative adversarial networks. In: ICLR (2017)Google Scholar
  23. 23.
    Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. In: ICLR (2018)Google Scholar
  24. 24.
    Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
  25. 25.
    Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: ICML, pp. 1278–1286 (2014)Google Scholar
  26. 26.
    Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training gans. In: NIPS, pp. 2234–2242 (2016)Google Scholar
  27. 27.
    Warde-Farley, D., Bengio, Y.: Improving generative adversarial networks with denoising feature matching. In: ICLR (2017)Google Scholar
  28. 28.
    Wu, Y., Burda, Y., Salakhutdinov, R., Grosse, R.: On the quantitative analysis of decoder-based generative models. In: ICLR (2017)Google Scholar
  29. 29.
    Yazıcı, Y., Foo, C.S., Winkler, S., Yap, K.H., Piliouras, G., Chandrasekhar, V.: The unusual effectiveness of averaging in gan training. arXiv preprint arXiv:1806.04498 (2018)
  30. 30.
    Zhao, J., Mathieu, M., LeCun, Y.: Energy-based generative adversarial network. In: ICLR (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.ST Electronics - SUTD Cyber Security LaboratorySingapore University of Technology and DesignSingaporeSingapore

Personalised recommendations