The International Arab Journal of Information Technology (IAJIT)

..............................
..............................
..............................


Generative Adversarial Networks with Data Augmentation and Multiple Penalty Areas for Image Synthesis

The quality of generated images is one of the significant criteria for Generative Adversarial Networks (GANs) evaluation in image synthesis research. Previous researches proposed a great many tricks to modify the model structure or loss functions. However, seldom of them consider the effect of combination of data augmentation and multiple penalty areas on image quality improvement. This research introduces a GAN architecture based on data augmentation, in order to make the model fulfill 1-Lipschitz constraints, it proposes to consider these additional data included into the penalty areas which can improve ability of discriminator and generator. With the help of these techniques, compared with previous model Deep Convolutional GAN (DCGAN) and Wasserstein GAN with gradient penalty (WGAN-GP), the model proposed in this research can get lower Frechet Inception Distance score (FID) score 2.973 and 2.941 on celebA and LSUN towers at 64×64 resolution respectively which proves that this model can produce high visual quality results.

  1. Arjovsky M., Chintala S., and Bottou L., “Wasserstein Generative Adversarial Networks,” in Proceedings of the 34th International Conference on Machine Learning, Sydney, pp. 214-23, 2017.
  1. Barratt S. and Sharma R., “A Note on the Inception Score,” ArXiv:180101973 [Cs, Stat], 2018.
  1. Berthelot D., Schumm T., Metz L., “BEGAN: Boundary Equilibrium Generative Adversarial Networks,” ArXiv:170310717 [Cs, Stat], 2017.
  1. Bhuiyan A. and Khan A., “Image Quality Assessment Employing RMS Contrast and Histogram Similarity,” The International Arab Journal of Information Technology, vol. 15, no. 6, pp. 983-989, 2018.
  1. Chen X., Duan Y., Houthooft R., Schulman J., Sutskever I., and Abbeel P., “InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets,” Advances in Neural Information Processing Systems, vol. 29, 2016.
  1. Dinh L., Krueger D., and Bengio Y., “NICE: Non-linear Independent Components Estimation,” ArXiv:14108516 [Cs], 2015.
  1. Dinh L., Sohl-Dickstein J., and Bengio S., “Density Estimation Using Real NVP,” ArXiv:160508803 [Cs, Stat], 2017.
  2. Donahue J., Krähenbühl P., Darrell T., “Adversarial Feature Learning,” ArXiv:160509782 [Cs, Stat], 2017.
  3. Goodfellow I., Pouget-Abadie J., Mirza M., Xu B., Warde-Farley D., Ozair S., Courville A., and Bengio Y., “Generative Adversarial Networks,” Communications of the ACM, vol. 13, pp. 139-144, 2020.
  4. Gulrajani I., Ahmed F., Arjovsky M., Dumoulin V., and Courville A., “Improved Training of Wasserstein GANs,” Advances in Neural Information Processing Systems, vol. 30, 2017.
  5. Heusel M., Ramsauer H., Unterthiner T., Nessler B., and Hochreiter S., “GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium,” Advances in Neural Information Processing Systems, vol. 30, 2017.
  6. Jolicoeur-Martineau A., “The Relativistic Discriminator: A Key Element Missing From Standard GAN,” ArXiv:180700734 [Cs, Stat], 2018.
  7. Larsen A., Sønderby S., Larochelle H., and Winther O., “Autoencoding Beyond Pixels Using A Learned Similarity Metric,” in Proceedings of the 33rd International Conference on International Conference on Machine Learning, New York, pp. 1558-1566, 2016.
  8. Liu Z., Luo P., Wang X., and Tang X., “Deep Learning Face Attributes in the Wild,” ArXiv:14117766 [Cs], 2015.
  9. Maas A., Hannun A., and Ng A., “Rectifier Nonlinearities Improve Neural Network Acoustic Models,” in Proceedings of the International Conference on Machine Learning, Atlanta, 2013.
  10. Mao X., Li Q., Xie H., Lau R., Wang Z., and Smolley S., “Least Squares Generative Adversarial Networks,” in Proceedings of the IEEE International Conference on Computer Vision, Venice, pp. 2794-2802, 2017.
  11. Mirza M. and Osindero S., “Conditional Generative Adversarial Nets,” ArXiv:14111784 [Cs, Stat], 2014.
  12. Miyato T., Kataoka T., Koyama M., and Yoshida Y., “Spectral Normalization for Generative Adversarial Networks,” ArXiv:180205957 [Cs, Stat], 2018.
  13. Odena A., Olah C., and Shlens J., “Conditional Image Synthesis with Auxiliary Classifier GANs,” in Proceedings of the 34th International Conference on Machine Learning, Sydney, pp. 2642-2651, 2017.
  14. Van den Oord A., Kalchbrenner N., Espeholt L, Kavukcuoglu K., Vinyals O., and Graves A., “Conditional Image Generation with PixelCNN Decoders,” Advances in Neural Information Processing Systems, vol. 29, 2016.
  15. Radford A., Metz L., and Chintala S., “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,” ArXiv:151106434 [Cs], 2016.
  16. Rezende D. and Mohamed S., “Variational Inference with Normalizing Flows,” in Proceedings of the 32nd International Conference on Machine Learning, Lille, pp. 1530-1538, 2015.
  17. Rifai S., Vincent P., Muller X., Glorot X., and Bengio Y., “Contractive Auto-Encoders: Explicit Invariance during Feature Extraction,” in Proceedings of the 28th International Conference on Machine Learning, Bellevue, pp. 833-840, 2011.
  18. Salimans T., Goodfellow I., Zaremba W., Cheung V., Radford A., Chen X., and Chen X., “Improved Techniques for Training GANs,” Advances in Neural Information Processing Systems, vol. 29, 2016.
  19. Vincent P., Larochelle H., Bengio Y., and Manzagol P., “Extracting and Composing Robust Features with Denoising Autoencoders,” in Proceedings of the 25th International Conference on Machine Learning, Helsinki Finland, pp. 1096-1199, 2008.
  20. Yu F., Seff A., Zhang Y., Song S., Funkhouser T., and Xiao J., “LSUN: Construction of a Large-Scale Image Dataset using Deep Learning with Humans in the Loop,” ArXiv:150603365 [Cs], 2016.
  21. Zhao J., Mathieu M., and LeCun Y., “Energy-based Generative Adversarial Network,” ArXiv:160903126 [Cs, Stat], 2017.