Skip to main content
Erschienen in:
Buchtitelbild

2019 | OriginalPaper | Buchkapitel

Deep Generative Models for Image Generation: A Practical Comparison Between Variational Autoencoders and Generative Adversarial Networks

verfasst von : Mohamed El-Kaddoury, Abdelhak Mahmoudi, Mohammed Majid Himmi

Erschienen in: Mobile, Secure, and Programmable Networking

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Deep Learning models can achieve impressive performance in supervised learning but not for unsupervised one. In image generation problem for example, we have no concrete target vector. Generative models have been proven useful for solving this kind of issues. In this paper, we will compare two types of generative models: Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). We apply those methods to different data sets to point out their differences and see their capabilities and limits as well. We find that, while VAEs are easier and faster to train, their results are in general more blurry than the images generated by GANs. These last are more realistic but noisy.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Goyal, P., Hu, Z., Liang, X., Wang, C., Xing, E.: Nonparametric variational autoencoders for hierarchical representation learning. arXiv:1703.07027 (2017) Goyal, P., Hu, Z., Liang, X., Wang, C., Xing, E.: Nonparametric variational autoencoders for hierarchical representation learning. arXiv:​1703.​07027 (2017)
2.
Zurück zum Zitat Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014) Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
4.
Zurück zum Zitat Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: ICML, pp. 1278–1286 (2014) Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: ICML, pp. 1278–1286 (2014)
5.
Zurück zum Zitat Gregor, K., Danihelka, I., Graves, A., Rezende, D.J., Wierstra, D.: DRAW: a recurrent neural network for image generation. arXiv preprint arXiv:1502.04623 (2015) Gregor, K., Danihelka, I., Graves, A., Rezende, D.J., Wierstra, D.: DRAW: a recurrent neural network for image generation. arXiv preprint arXiv:​1502.​04623 (2015)
6.
Zurück zum Zitat Bordes, A., Bottou, L., Gallinari, P.: SGD-QN: careful quasi-Newton stochastic gradient descent. J. Mach. Learn. Res. 10, 1737–1754 (2009)MathSciNetMATH Bordes, A., Bottou, L., Gallinari, P.: SGD-QN: careful quasi-Newton stochastic gradient descent. J. Mach. Learn. Res. 10, 1737–1754 (2009)MathSciNetMATH
7.
Zurück zum Zitat Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, University of Toronto (2009) Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, University of Toronto (2009)
8.
Zurück zum Zitat LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010) LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010)
9.
Zurück zum Zitat Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV), December 2015 Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV), December 2015
10.
Zurück zum Zitat Gu, X., Knutsson, H., Nilsson, M., Eklund, A.: Generating diffusion MRI scalar maps from T1 weighted images using generative adversarial networks. CoRR (2018) Gu, X., Knutsson, H., Nilsson, M., Eklund, A.: Generating diffusion MRI scalar maps from T1 weighted images using generative adversarial networks. CoRR (2018)
11.
Zurück zum Zitat Abbasnejad, M.E., Dick, A., van den Hengel, A.: 2017 IEEE Conference on Computer Vision a (2017) Abbasnejad, M.E., Dick, A., van den Hengel, A.: 2017 IEEE Conference on Computer Vision a (2017)
12.
Zurück zum Zitat Yeh, R.A., Chen, C., Lim, T.Y., Schwing, A.G., Hasegawa-Johnson, M., Do, M.N.: Semantic image inpainting with deep generative models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5485–5493 (2017) Yeh, R.A., Chen, C., Lim, T.Y., Schwing, A.G., Hasegawa-Johnson, M., Do, M.N.: Semantic image inpainting with deep generative models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5485–5493 (2017)
13.
Zurück zum Zitat Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. arXiv preprint arXiv:1611.07004 (2016) Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. arXiv preprint arXiv:​1611.​07004 (2016)
14.
Zurück zum Zitat Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network (2016) Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network (2016)
15.
Zurück zum Zitat Zhao, F., Feng, J., Zhao, J., Yang, W., Yan, S.: Robust lstmautoencoders for face de-occlusion in the wild. IEEE Trans. Image Process. 27(2), 778–790 (2018)MathSciNetCrossRef Zhao, F., Feng, J., Zhao, J., Yang, W., Yan, S.: Robust lstmautoencoders for face de-occlusion in the wild. IEEE Trans. Image Process. 27(2), 778–790 (2018)MathSciNetCrossRef
16.
Zurück zum Zitat Press, O., Bar, A., Bogin, B., Berant, J., Wolf, L.: Language generation with recurrent generative adversarial networks without pre-training. arXiv preprint arXiv:1706.01399 (2017) Press, O., Bar, A., Bogin, B., Berant, J., Wolf, L.: Language generation with recurrent generative adversarial networks without pre-training. arXiv preprint arXiv:​1706.​01399 (2017)
17.
Zurück zum Zitat Yu, L., Zhang, W., Wang, J., Yu, Y.: SeqGAN: sequence generative adversarial nets with policy gradient. In: AAAI 2017, pp. 2852–2858 (2017) Yu, L., Zhang, W., Wang, J., Yu, Y.: SeqGAN: sequence generative adversarial nets with policy gradient. In: AAAI 2017, pp. 2852–2858 (2017)
18.
Zurück zum Zitat Barratt, S., Sharma, R.: A note on the inception score. In: ICML Workshop (2018) Barratt, S., Sharma, R.: A note on the inception score. In: ICML Workshop (2018)
Metadaten
Titel
Deep Generative Models for Image Generation: A Practical Comparison Between Variational Autoencoders and Generative Adversarial Networks
verfasst von
Mohamed El-Kaddoury
Abdelhak Mahmoudi
Mohammed Majid Himmi
Copyright-Jahr
2019
DOI
https://doi.org/10.1007/978-3-030-22885-9_1