Skip to main content

2018 | OriginalPaper | Buchkapitel

Wasserstein Divergence for GANs

verfasst von : Jiqing Wu, Zhiwu Huang, Janine Thoma, Dinesh Acharya, Luc Van Gool

Erschienen in: Computer Vision – ECCV 2018

Verlag: Springer International Publishing

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

search-config
loading …

Abstract

In many domains of computer vision, generative adversarial networks (GANs) have achieved great success, among which the family of Wasserstein GANs (WGANs) is considered to be state-of-the-art due to the theoretical contributions and competitive qualitative performance. However, it is very challenging to approximate the k-Lipschitz constraint required by the Wasserstein-1 metric (W-met). In this paper, we propose a novel Wasserstein divergence (W-div), which is a relaxed version of W-met and does not require the k-Lipschitz constraint. As a concrete application, we introduce a Wasserstein divergence objective for GANs (WGAN-div), which can faithfully approximate W-div through optimization. Under various settings, including progressive growing training, we demonstrate the stability of the proposed WGAN-div owing to its theoretical and practical advantages over WGANs. Also, we study the quantitative and visual performance of WGAN-div on standard image synthesis benchmarks, showing the superior performance of WGAN-div compared to the state-of-the-art methods.

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!

Anhänge
Nur mit Berechtigung zugänglich
Fußnoten
1
\(\mathcal {W}_{\mathbb {P}_{u}}^{'}\) is a family of special cases of Eq. 11 with a more restrictive function space \(C_c^{\infty }\).
 
Literatur
1.
Zurück zum Zitat Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014) Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)
2.
Zurück zum Zitat Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015) Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:​1511.​06434 (2015)
3.
Zurück zum Zitat Berthelot, D., Schumm, T., Metz, L.: BEGAN: boundary equilibrium generative adversarial networks. arXiv preprint arXiv:1703.10717 (2017) Berthelot, D., Schumm, T., Metz, L.: BEGAN: boundary equilibrium generative adversarial networks. arXiv preprint arXiv:​1703.​10717 (2017)
4.
Zurück zum Zitat Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., Smolley, S.P.: Least squares generative adversarial networks. arXiv preprint arXiv:1611.04076 (2016) Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., Smolley, S.P.: Least squares generative adversarial networks. arXiv preprint arXiv:​1611.​04076 (2016)
6.
Zurück zum Zitat Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICML (2017) Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICML (2017)
7.
Zurück zum Zitat Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of wasserstein GANs. In: NIPS, pp. 5767–5777 (2017) Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of wasserstein GANs. In: NIPS, pp. 5767–5777 (2017)
8.
Zurück zum Zitat Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018) Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:​1802.​05957 (2018)
9.
Zurück zum Zitat Wei, X., Gong, B., Liu, Z., Lu, W., Wang, L.: Improving the improved training of wasserstein GANs: a consistency term and its dual effect. In: ICLR (2018) Wei, X., Gong, B., Liu, Z., Lu, W., Wang, L.: Improving the improved training of wasserstein GANs: a consistency term and its dual effect. In: ICLR (2018)
10.
Zurück zum Zitat Roth, K., Lucchi, A., Nowozin, S., Hofmann, T.: Stabilizing training of generative adversarial networks through regularization. In: NIPS, pp. 2015–2025 (2017) Roth, K., Lucchi, A., Nowozin, S., Hofmann, T.: Stabilizing training of generative adversarial networks through regularization. In: NIPS, pp. 2015–2025 (2017)
11.
Zurück zum Zitat Nowozin, S., Cseke, B., Tomioka, R.: f-GAN: training generative neural samplers using variational divergence minimization. In: NIPS, pp. 271–279 (2016) Nowozin, S., Cseke, B., Tomioka, R.: f-GAN: training generative neural samplers using variational divergence minimization. In: NIPS, pp. 271–279 (2016)
12.
Zurück zum Zitat Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV (2017) Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV (2017)
13.
Zurück zum Zitat Huang, X., Li, Y., Poursaeed, O., Hopcroft, J., Belongie, S.: Stacked generative adversarial networks. arXiv preprint arXiv:1612.04357 (2016) Huang, X., Li, Y., Poursaeed, O., Hopcroft, J., Belongie, S.: Stacked generative adversarial networks. arXiv preprint arXiv:​1612.​04357 (2016)
14.
Zurück zum Zitat Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017) Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:​1710.​10196 (2017)
15.
Zurück zum Zitat Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. In: NIPS Workshop, vol. 2016 (2017) Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. In: NIPS Workshop, vol. 2016 (2017)
18.
Zurück zum Zitat Rothe, R., Timofte, R., Gool, L.V.: Deep expectation of real and apparent age from a single image without facial landmarks. Int. J. Comput. Vis. (IJCV) 126(2–4), 144–157 (2016)MathSciNet Rothe, R., Timofte, R., Gool, L.V.: Deep expectation of real and apparent age from a single image without facial landmarks. Int. J. Comput. Vis. (IJCV) 126(2–4), 144–157 (2016)MathSciNet
19.
Zurück zum Zitat Evans, L.C.: Partial differential equations and monge-kantorovich mass transfer. Curr. Dev. Math. 1997(1), 65–126 (1997)CrossRef Evans, L.C.: Partial differential equations and monge-kantorovich mass transfer. Curr. Dev. Math. 1997(1), 65–126 (1997)CrossRef
20.
Zurück zum Zitat He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016) He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
22.
Zurück zum Zitat Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: ICCV (2015) Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: ICCV (2015)
23.
Zurück zum Zitat Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: LSUN: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015) Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: LSUN: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:​1506.​03365 (2015)
24.
Zurück zum Zitat Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NIPS, pp. 6629–6640 (2017) Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NIPS, pp. 6629–6640 (2017)
25.
Zurück zum Zitat Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NIPS, pp. 2234–2242 (2016) Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NIPS, pp. 2234–2242 (2016)
26.
Zurück zum Zitat Lucic, M., Kurach, K., Michalski, M., Gelly, S., Bousquet, O.: Are GANs created equal? A large-scale study. arXiv preprint arXiv:1711.10337 (2017) Lucic, M., Kurach, K., Michalski, M., Gelly, S., Bousquet, O.: Are GANs created equal? A large-scale study. arXiv preprint arXiv:​1711.​10337 (2017)
27.
Zurück zum Zitat Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015) Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:​1502.​03167 (2015)
Metadaten
Titel
Wasserstein Divergence for GANs
verfasst von
Jiqing Wu
Zhiwu Huang
Janine Thoma
Dinesh Acharya
Luc Van Gool
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-030-01228-1_40

Premium Partner