Advertisement

Semi-supervised Learning with Bidirectional GANs

  • Maciej ZamorskiEmail author
  • Maciej Zięba
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11431)

Abstract

In this work we introduce a novel approach to train Bidirectional Generative Adversarial Model (BiGAN) in a semi-supervised manner. The presented method utilizes triplet loss function as an additional component of the objective function used to train discriminative data representation in the latent space of the BiGAN model. This representation can be further used as a seed for generating artificial images, but also as a good feature embedding for classification and image retrieval tasks. We evaluate the quality of the proposed method in the two mentioned challenging tasks using two benchmark datasets: CIFAR10 and SVHN.

Keywords

Generative models Triplet learning Generative adversarial networks Image retrieval 

References

  1. 1.
    Donahue, J., Krähenbühl, P., Darrell, T.: Adversarial feature learning. arXiv preprint arXiv:1605.09782 (2016)
  2. 2.
    Dumoulin, V., et al.: Adversarially learned inference. arXiv preprint arXiv:1606.00704 (2016)
  3. 3.
    Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  4. 4.
    Hoffer, E., Ailon, N.: Deep metric learning using triplet network. In: Feragen, A., Pelillo, M., Loog, M. (eds.) SIMBAD 2015. LNCS, vol. 9370, pp. 84–92. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24261-3_7CrossRefGoogle Scholar
  5. 5.
    Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)
  6. 6.
    Kumar, B., Carneiro, G., Reid, I., et al.: Learning local image descriptors with deep siamese and triplet convolutional networks by minimising global loss functions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5385–5394 (2016)Google Scholar
  7. 7.
    van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579–2605 (2008)zbMATHGoogle Scholar
  8. 8.
    Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
  9. 9.
    Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, pp. 2234–2242 (2016)Google Scholar
  10. 10.
    Yao, T., Long, F., Mei, T., Rui, Y.: Deep semantic-preserving and ranking-based hashing for image retrieval. In: IJCAI, pp. 3931–3937 (2016)Google Scholar
  11. 11.
    Zhuang, B., Lin, G., Shen, C., Reid, I.: Fast training of triplet-based deep binary embedding networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5955–5964 (2016)Google Scholar
  12. 12.
    Zieba, M., Semberecki, P., El-Gaaly, T., Trzcinski, T.: BinGAN: learning compact binary descriptors with a regularized GAN. arXiv preprint arXiv:1806.06778 (2018)
  13. 13.
    Zieba, M., Wang, L.: Training triplet networks with GAN. arXiv preprint arXiv:1704.02227 (2017)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer Science, Faculty of Computer Science and ManagementWrocław University of Science and TechnologyWrocławPoland
  2. 2.Tooploox Ltd.WrocławPoland

Personalised recommendations