Advertisement

Enhancing Symmetry in GAN Generated Fashion Images

  • Vishnu MakkapatiEmail author
  • Arun Patro
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10630)

Abstract

Generative adversarial networks (GANs) are being used in several fields to produce new images that are similar to those in the input set. We train a GAN to generate images of articles pertaining to fashion that have inherent horizontal symmetry in most cases. Variants of GAN proposed so far do not exploit symmetry and hence may or may not produce fashion designs that are realistic. We propose two methods to exploit symmetry, leading to better designs - (a) Introduce a new loss to check if the flipped version of the generated image is equivalently classified by the discriminator (b) Invert the flipped version of the generated image to reconstruct an image with minimal distortions. We present experimental results to show that imposing the new symmetry loss produces better looking images and also reduces the training time.

Keywords

Generative Adversarial Networks Deep learning Symmetry loss Generator Discriminator 

References

  1. 1.
    Bora, A., Jalal, A., Price, E., Dimakis, A.G.: Compressed sensing using generative models. arXiv preprint arXiv:1703.03208 (2017)
  2. 2.
    Creswell, A., Bharath, A.A.: Inverting the generator of a generative adversarial network. arXiv preprint arXiv:1611.05644 (2016)
  3. 3.
    Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  4. 4.
    Kim, T.: A tensorflow implementation of deep convolutional generative adversarial networks. https://github.com/carpedm20/DCGAN-tensorflow
  5. 5.
    Lipton, Z.C., Tripathi, S.: Precise recovery of latent vectors from generative adversarial networks. arXiv preprint arXiv:1702.04782 (2017)
  6. 6.
    Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Myntra Designs Pvt. Ltd.BengaluruIndia
  2. 2.Department of Electrical EngineeringIndian Institute of Technology KharagpurKharagpurIndia

Personalised recommendations