Skip to main content
Erschienen in:
Buchtitelbild

2020 | OriginalPaper | Buchkapitel

Unsupervised Representation Learning Based on Generative Adversarial Networks

verfasst von : Shi Xu, Jia Wang

Erschienen in: Digital TV and Wireless Multimedia Communication

Verlag: Springer Singapore

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

search-config
loading …

Abstract

This paper introduces a novel model for learning disentangled representations based on Generative Adversarial Networks. The training model is unsupervised without identity information. Unlike InfoGAN in which the disentangled representation is learnt by getting the variational lower bound of the mutual information indirectly, our method introduces a direct way by adding predicting networks and encoder into GANs and measuring the correlation among the encoder outputs. Experiment results on MNIST demonstrate that the proposed model is more generalizable and robust than InfoGAN. With experiments on Celeba-HQ, we show that our model can extract factorial features with complicate datasets and produce results comparable to supervised models.

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 Agakov, D.B.F.: The IM algorithm: a variational approach to information maximization. In: Advances in Neural Information Processing Systems, vol. 16, p. 201 (2004)CrossRef Agakov, D.B.F.: The IM algorithm: a variational approach to information maximization. In: Advances in Neural Information Processing Systems, vol. 16, p. 201 (2004)CrossRef
2.
Zurück zum Zitat Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214–223 (2017) Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214–223 (2017)
3.
Zurück zum Zitat Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013)CrossRef Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013)CrossRef
4.
5.
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)
6.
Zurück zum Zitat Bourlard, H., Kamp, Y.: Auto-association by multilayer perceptrons and singular value decomposition. Biol. Cybern. 59(4–5), 291–294 (1988)MathSciNetCrossRef Bourlard, H., Kamp, Y.: Auto-association by multilayer perceptrons and singular value decomposition. Biol. Cybern. 59(4–5), 291–294 (1988)MathSciNetCrossRef
7.
Zurück zum Zitat Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2172–2180 (2016) Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2172–2180 (2016)
9.
Zurück zum Zitat Endres, D.M., Schindelin, J.E.: A new metric for probability distributions. IEEE Trans. Inf. Theory 49, 1858–1860 (2003)MathSciNetCrossRef Endres, D.M., Schindelin, J.E.: A new metric for probability distributions. IEEE Trans. Inf. Theory 49, 1858–1860 (2003)MathSciNetCrossRef
10.
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)
11.
Zurück zum Zitat Hinton, G.E., Zemel, R.S.: Autoencoders, minimum description length and Helmholtz free energy. In: Advances in Neural Information Processing Systems, pp. 3–10 (1994) Hinton, G.E., Zemel, R.S.: Autoencoders, minimum description length and Helmholtz free energy. In: Advances in Neural Information Processing Systems, pp. 3–10 (1994)
12.
Zurück zum Zitat Jolliffe, I.: Principal Component Analysis. Springer, New York (2011)MATH Jolliffe, I.: Principal Component Analysis. Springer, New York (2011)MATH
13.
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 LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRef LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRef
16.
Zurück zum Zitat Liu, Y., Wei, F., Shao, J., Sheng, L., Yan, J., Wang, X.: Exploring disentangled feature representation beyond face identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2080–2089 (2018) Liu, Y., Wei, F., Shao, J., Sheng, L., Yan, J., Wang, X.: Exploring disentangled feature representation beyond face identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2080–2089 (2018)
17.
Zurück zum Zitat Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3730–3738 (2015) Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3730–3738 (2015)
18.
Zurück zum Zitat Maaløe, L., Sønderby, C.K., Sønderby, S.K., Winther, O.: Improving semi-supervised learning with auxiliary deep generative models. In: NIPS Workshop on Advances in Approximate Bayesian Inference (2015) Maaløe, L., Sønderby, C.K., Sønderby, S.K., Winther, O.: Improving semi-supervised learning with auxiliary deep generative models. In: NIPS Workshop on Advances in Approximate Bayesian Inference (2015)
19.
Zurück zum Zitat MacQueen, J., et al.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Oakland, CA, USA, vol. 1, pp. 281–297 (1967) MacQueen, J., et al.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Oakland, CA, USA, vol. 1, pp. 281–297 (1967)
20.
Zurück zum Zitat Makhzani, A., Frey, B.: \(k\)-Sparse autoencoders. Comput. Sci. (2014) Makhzani, A., Frey, B.: \(k\)-Sparse autoencoders. Comput. Sci. (2014)
21.
22.
Zurück zum Zitat Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013) Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:​1301.​3781 (2013)
23.
Zurück zum Zitat Mitra, P., Murthy, C., Pal, S.K.: Unsupervised feature selection using feature similarity. IEEE Trans. Pattern Anal. Mach. Intell. 24(3), 301–312 (2002)CrossRef Mitra, P., Murthy, C., Pal, S.K.: Unsupervised feature selection using feature similarity. IEEE Trans. Pattern Anal. Mach. Intell. 24(3), 301–312 (2002)CrossRef
24.
Zurück zum Zitat Ng, A., et al.: Sparse autoencoder. In: CS294A Lecture Notes, vol. 72, pp. 1–19 (2011) Ng, A., et al.: Sparse autoencoder. In: CS294A Lecture Notes, vol. 72, pp. 1–19 (2011)
25.
Zurück zum Zitat Rasmus, A., Berglund, M., Honkala, M., Valpola, H., Raiko, T.: Semi-supervised learning with ladder networks. In: Advances in Neural Information Processing Systems, pp. 3546–3554 (2015) Rasmus, A., Berglund, M., Honkala, M., Valpola, H., Raiko, T.: Semi-supervised learning with ladder networks. In: Advances in Neural Information Processing Systems, pp. 3546–3554 (2015)
26.
Zurück zum Zitat Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1096–1103. ACM (2008) Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1096–1103. ACM (2008)
27.
Metadaten
Titel
Unsupervised Representation Learning Based on Generative Adversarial Networks
verfasst von
Shi Xu
Jia Wang
Copyright-Jahr
2020
Verlag
Springer Singapore
DOI
https://doi.org/10.1007/978-981-15-3341-9_6

Neuer Inhalt