Advertisement

On Conditioning GANs to Hierarchical Ontologies

  • Hamid Eghbal-zadeh
  • Lukas FischerEmail author
  • Thomas Hoch
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1062)

Abstract

The recent success of Generative Adversarial Networks (GAN) is a result of their ability to generate high quality images given samples from a latent space. One of the applications of GANs is to generate images from a text description, where the text is first encoded and further used for the conditioning in the generative model. In addition to text, conditional generative models often use label information for conditioning. Hence, the structure of the meta-data and the ontology of the labels is important for such models. In this paper, we propose Ontology Generative Adversarial Networks (O-GANs) to handle the complexities of the data with label ontology. We evaluate our model on a dataset of fashion images with hierarchical label structure. Our results suggest that the incorporation of the ontology, leads to better image quality as measured by Fréchet Inception Distance and Inception Score. Additionally, we show that the O-GAN better matches the generated images to their conditioning text, compared to models that do not incorporate the label ontology.

Keywords

Generative Adversarial Networks Text-to-image synthesis Ontology-driven deep learning 

References

  1. 1.
    Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: CVPR 2009, pp. 248–255 (2009)Google Scholar
  2. 2.
    Gulrajani, I., et al.: Improved training of Wasserstein GANs. In: NIPS 2017, pp. 5769–5779 (2017)Google Scholar
  3. 3.
    Heusel, M., et al.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: NIPS 2017, pp. 6629–6640 (2017)Google Scholar
  4. 4.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  5. 5.
    Karras, T., et al.: Progressive growing of GANs for improved quality, stability, and variation. In: ICLR 2018 (2018)Google Scholar
  6. 6.
    Kuang, Z., et al.: Ontology-driven hierarchical deep learning for fashion recognition. In: MIPR 2018, pp. 19–24 (2018)Google Scholar
  7. 7.
    Pennington, J., et al.: Glove: global vectors for word representation. In: EMNLP 2014, pp. 1532–1543 (2014)Google Scholar
  8. 8.
    Rostamzadeh, N., et al.: Fashion-Gen: the generative fashion dataset and challenge. arXiv:1806.08317 (2018)
  9. 9.
    Salimans, T., et al.: Improved techniques for training GANs. In: NIPS 2016, pp. 2234–2242 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.LIT AI Lab & Institute of Computational PerceptionJohannes Kepler University LinzLinzAustria
  2. 2.Software Competence Center Hagenberg GmbH (SCCH)HagenbergAustria

Personalised recommendations