Advertisement

DesIGN: Design Inspiration from Generative Networks

  • Othman Sbai
  • Mohamed Elhoseiny
  • Antoine Bordes
  • Yann LeCun
  • Camille CouprieEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11131)

Abstract

Can an algorithm create original and compelling fashion designs to serve as an inspirational assistant? To help answer this question, we design and investigate different image generation models associated with different loss functions to boost novelty in fashion generation. The dimensions of our explorations include: (i) different Generative Adversarial Networks architectures that start from noise vectors to generate fashion items, (ii) a new loss function that encourages novelty, and (iii) a generation process following the key elements of fashion design (disentangling shape and texture). A key challenge of this study is the evaluation of generated designs and the retrieval of best ones, hence we put together an evaluation protocol associating automatic metrics and human experimental studies. We show that our proposed creativity loss yields better overall appreciation than the one employed in Creative Adversarial Networks. In the end, about 61% of our images are thought to be created by human designers rather than by a computer while also being considered original per our human subject experiments, and our proposed loss scores the highest compared to existing losses in both novelty and likability.

Keywords

Fashion image generation Generative adversarial networks 

References

  1. 1.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)Google Scholar
  2. 2.
    Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: CVPR (2016)Google Scholar
  3. 3.
    Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484 (2016)CrossRefGoogle Scholar
  4. 4.
    Briot, J.P., Hadjeres, G., Pachet, F.: Deep learning techniques for music generation-a survey. arXiv:1709.01620 (2017)
  5. 5.
    Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: CVPR (2016)Google Scholar
  6. 6.
    Dumoulin, V., et al.: A learned representation for artistic style. In: ICLR (2017)Google Scholar
  7. 7.
    Ha, D., Eck, D.: A neural representation of sketch drawings. In: ICLR (2018)Google Scholar
  8. 8.
    Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)Google Scholar
  9. 9.
    Reed, S.E., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.: Learning what and where to draw. In: NIPS (2016)Google Scholar
  10. 10.
    Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: ICML (2017)Google Scholar
  11. 11.
    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
  12. 12.
    Elgammal, A., Liu, B., Elhoseiny, M., Mazzone, M.: Creative adversarial networks. In: ICCC (2017)Google Scholar
  13. 13.
    Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: ICLR (2016)Google Scholar
  14. 14.
    Date, P., Ganesan, A., Oates, T.: Fashioning with networks: neural style transfer to design clothes. In: KDD ML4Fashion workshop (2017)Google Scholar
  15. 15.
    Zhu, S., Fidler, S., Urtasun, R., Lin, D., Loy, C.C.: Be your own prada: fashion synthesis with structural coherence. In: ICCV (2017)Google Scholar
  16. 16.
    Lassner, C., Pons-Moll, G., Gehler, P.V.: A generative model of people in clothing. In: ICCV (2017)Google Scholar
  17. 17.
    Isola, P., Zhu, J., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)Google Scholar
  18. 18.
    Zhou, Z., Zhang, W., Wang, J.: Inception score, label smoothing, gradient vanishing and -log(d(x)) alternative. arXiv:1708.01729 (2017)
  19. 19.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv:1512.03385 (2015)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Othman Sbai
    • 1
    • 2
  • Mohamed Elhoseiny
    • 2
  • Antoine Bordes
    • 2
  • Yann LeCun
    • 2
    • 3
  • Camille Couprie
    • 2
    Email author
  1. 1.Université Paris Est, Ecole des ponts, ImagineMarne-la-ValléeFrance
  2. 2.Facebook AI ResearchParisFrance
  3. 3.New York UniversityNew York CityUSA

Personalised recommendations