Skip to main content
SpringerLink
Log in

Quaternion Generative Adversarial Networks

  • Chapter
  • First Online:
Generative Adversarial Learning: Architectures and Applications

Part of the book series: Intelligent Systems Reference Library ((ISRL,volume 217))

Abstract

Latest Generative Adversarial Networks (GANs) are gathering outstanding results through a large-scale training, thus employing models composed of millions of parameters requiring extensive computational capabilities. Building such huge models undermines their replicability and increases the training instability. Moreover, multi-channel data, such as images or audio, are usually processed by real-valued convolutional networks that flatten and concatenate the input, often losing intra-channel spatial relations. To address these issues related to complexity and information loss, we propose a family of quaternion-valued generative adversarial networks (QGANs). QGANs exploit the properties of quaternion algebra, e.g., the Hamilton product, that allows to process channels as a single entity and capture internal latent relations, while reducing by a factor of 4 the overall number of parameters. We show how to design QGANs and to extend the proposed approach even to advanced models. We compare the proposed QGANs with real-valued counterparts on several image generation benchmarks. Results show that QGANs are able to obtain better FID scores than real-valued GANs and to generate visually pleasing images. Furthermore, QGANs save up to \(75\%\) of the training parameters. We believe these results may pave the way to novel, more accessible, GANs capable of improving performance and saving computational resources.

This work has been supported by “Progetti di Ricerca Grandi” of Sapienza University of Rome under grant number RG11916B88E1942F.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 149.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 199.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 199.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    The implementation of the QGANs is available online at https://github.com/eleGAN23/QGAN.

References

  1. Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN (2017). arXiv:1701.07875v3

  2. Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Representations (ICLR) (2019)

    Google Scholar 

  3. Chen, T., Zhai, X., Ritter, M., Lucic, M., Houlsby, N.: Self-supervised GANs via auxiliary rotation loss. In: IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12146–12155 (2019)

    Google Scholar 

  4. Cheong Took, C., Mandic, D.P.: Augmented second-order statistics of quaternion random signals. Signal Process. 91(2), 214–224 (2011)

    Article  Google Scholar 

  5. Chernov, V.: Discrete orthogonal transforms with data representation in composition algebras. In: Proceedings of the Scandinavian Conference on Image Analysis, pp. 357–364 (1995)

    Google Scholar 

  6. Comminiello, D., Lella, M., Scardapane, S., Uncini, A.: Quaternion convolutional neural networks for detection and localization of 3D sound events. In: IEEE International Conference on Acoustics, Speech and Signal Process. (ICASSP), pp. 8533–8537. Brighton, UK (2019)

    Google Scholar 

  7. Ell, T.A., Sangwine, S.J.: Quaternion involutions and anti-involutions. Comput. Math. Appl. 53(1), 137–143 (2007)

    Article  MathSciNet  Google Scholar 

  8. Gaudet, C., Maida, A.: Deep quaternion networks. In: IEEE International Joint Conference on Neural Network (IJCNN). Rio de Janeiro, Brazil (2018)

    Google Scholar 

  9. Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)

    Google Scholar 

  10. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: 27th International Conference on Neural Information Processing Systems (NIPS), vol. 2, pp. 2672–2680. MIT Press, Cambridge, MA, USA (2014)

    Google Scholar 

  11. Gouk, H., Frank, E., Pfahringer, B., Cree, M.J.: Regularisation of neural networks by enforcing Lipschitz continuity. Mach. Learn. 110(2), 393–416 (2021)

    Article  MathSciNet  Google Scholar 

  12. Grassucci, E., Comminiello, D., Uncini, A.: An information-theoretic perspective on proper quaternion variational autoencoders. Entropy 23(7) (2021)

    Google Scholar 

  13. Grassucci, E., Comminiello, D., Uncini, A.: A quaternion-valued variational autoencoder. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto, Canada (2021)

    Google Scholar 

  14. Grassucci, E., Scardapane, S., Comminiello, D., Uncini, A.: Flexible generative adversarial networks with non-parametric activation functions. In: Progress in Artificial Intelligence and Neural Systems, vol. 184. Smart Innovation, Systems and Technologies, Springer (2021)

    Google Scholar 

  15. Gui, J., Sun, Z., Wen, Y., Tao, D., Ye, J.P.: A review on generative adversarial networks: algorithms, theory, and applications (2020). arXiv:2001.06937v1

  16. Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems (NIPS) (2017)

    Google Scholar 

  17. He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1026–1034 (2015)

    Google Scholar 

  18. 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: Neural Information Processing Systems (NIPS), pp. 6626–6637 (2017)

    Google Scholar 

  19. Hoffmann, J., Schmitt, S., Osindero, S., Simonyan, K., Elsen, E.: AlgebraNets (2020). arXiv:2006.07360v2

  20. Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (ICML), pp. 448–456. JMLR.org (2015)

    Google Scholar 

  21. Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: International Conference on Learning Representations (ICLR) (2018)

    Google Scholar 

  22. Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 4401–4410. Computer Vision Foundation/IEEE (2019)

    Google Scholar 

  23. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8107–8116. IEEE (2020)

    Google Scholar 

  24. Kingma, D.P., Welling, M.: Auto-encoding variational Bayes, pp. 1–14 (2014). arXiv:1312.6114v10

  25. Kurach, K., Lucic, M., Zhai, X., Michalski, M., Gelly, S.: A large-scale study on regularization and normalization in GANs. In: International Conference on Machine Learning (ICML) (2019)

    Google Scholar 

  26. Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks (2018). arXiv:1802.05957v1

  27. Parcollet, T., Morchid, M., Linarès, G.: Quaternion convolutional neural networks for heterogeneous image processing. In: IEEE International Conference on Acoustics, Speech and Signal Process. (ICASSP), pp. 8514–8518. Brighton, UK (2019)

    Google Scholar 

  28. Parcollet, T., Morchid, M., Linarès, G.: A survey of quaternion neural networks. Art. Intell. Rev. (2019)

    Google Scholar 

  29. Parcollet, T., Ravanelli, M., Morchid, M., Linarès, G., Trabelsi, C., De Mori, R., Bengio, Y.: Quaternion recurrent neural networks. In: International Conference on Learning Representations (ICLR), pp. 1–19. New Orleans, LA (2019)

    Google Scholar 

  30. Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks (2016). arXiv:1511.06434v2

  31. Salimans, T., Goodfellow, I.J., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Neural Information Processing Systems (NIPS), pp. 2234–2242 (2016)

    Google Scholar 

  32. Schmidhuber, J.: A possibility for implementing curiosity and boredom in model-building neural controllers. In: Proceedings of the First International Conference on Simulation of Adaptive Behavior on From Animals to Animats, pp. 222–227. MIT Press, Cambridge, MA, USA (1991)

    Google Scholar 

  33. Schmidhuber, J.: Generative adversarial networks are special cases of artificial curiosity (1990) and also closely related to predictability minimization (1991). Neural Netw. 127, 58–66 (2020)

    Article  Google Scholar 

  34. Schönfeld, E., Schiele, B., Khoreva, A.: A U-Net based discriminator for generative adversarial networks. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8207–8216 (2020)

    Google Scholar 

  35. Sfikas, G., Giotis, A.P., Retsinas, G., Nikou, C.: Quaternion generative adversarial networks for inscription detection in byzantine monuments. In: Pattern Recognition. ICPR International Workshops and Challenges, pp. 171–184. Springer International Publishing (2021)

    Google Scholar 

  36. Vecchi, R., Scardapane, S., Comminiello, D., Uncini, A.: Compressing deep-quaternion neural networks with targeted regularisation. CAAI Trans. Intell. Technol. 5(3), 172–176 (2020)

    Article  Google Scholar 

  37. Vìa, J., Ramìrez, D., Santamarìa, I.: Proper and widely linear processing of quaternion random vectors. IEEE Trans. Inf. Theory 56(7), 3502–3515 (2010)

    Article  Google Scholar 

  38. Ward, J.P.: Quaternions and Cayley Numbers. Algebra and Applications. Mathematics and Its Applications, vol. 403. Kluwer Academic Publishers, Dordrecht (1997)

    Google Scholar 

  39. Yin, Q., Wang, J., Luo, X., Zhai, J., Jha, S.K., Shi, Y.: Quaternion convolutional neural network for color image classification and forensics. IEEE Access 7, 20293–20301 (2019)

    Article  Google Scholar 

  40. Zhang, H., Goodfellow, I.J., Metaxas, D.N., Odena, A.: Self-attention generative adversarial networks. In: International Conference on Machine Learning (ICML), Proceedings of Machine Learning Research, vol. 97, pp. 7354–7363. PMLR (2019)

    Google Scholar 

  41. Zhang, H., Zhang, Z., Odena, A., Lee, H.: Consistency regularization for generative adversarial networks. In: International Conference on Machine Learning (ICML) (2020)

    Google Scholar 

  42. Zhou, Z., Liang, J., Song, Y., Yu, L., Wang, H., Zhang, W., Yu, Y., Zhang, Z.: Lipschitz generative adversarial nets. In: International Conference on Machine Learning (ICML), Proceedings of Machine Learning Research, vol. 97, pp. 7584–7593. PMLR (2019)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Via Eudossiana 18, 00184, Rome, Italy

    Eleonora Grassucci, Edoardo Cicero & Danilo Comminiello

Authors
  1. Eleonora Grassucci
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Edoardo Cicero
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Danilo Comminiello
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Eleonora Grassucci .

Editor information

Editors and Affiliations

  1. Department of Electrical and Computer Engineering and School of Computer Science, University of Windsor, Windsor, ON, Canada

    Roozbeh Razavi-Far

  2. SeeChange.ai, Manchester, UK

    Ariel Ruiz-Garcia

  3. Centre for Computational Science and Mathematical Modelling, Coventry University, Coventry, Switzerland

    Vasile Palade

  4. The Swiss AI Lab, IDSIA, University of Lugano, USI & SUPSI, Lugano, Switzerland

    Juergen Schmidhuber

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Grassucci, E., Cicero, E., Comminiello, D. (2022). Quaternion Generative Adversarial Networks. In: Razavi-Far, R., Ruiz-Garcia, A., Palade, V., Schmidhuber, J. (eds) Generative Adversarial Learning: Architectures and Applications. Intelligent Systems Reference Library, vol 217. Springer, Cham. https://doi.org/10.1007/978-3-030-91390-8_4

Download citation

Publish with us

Policies and ethics

Search

Navigation