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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The implementation of the QGANs is available online at https://github.com/eleGAN23/QGAN.
References
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN (2017). arXiv:1701.07875v3
Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Representations (ICLR) (2019)
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)
Cheong Took, C., Mandic, D.P.: Augmented second-order statistics of quaternion random signals. Signal Process. 91(2), 214–224 (2011)
Chernov, V.: Discrete orthogonal transforms with data representation in composition algebras. In: Proceedings of the Scandinavian Conference on Image Analysis, pp. 357–364 (1995)
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)
Ell, T.A., Sangwine, S.J.: Quaternion involutions and anti-involutions. Comput. Math. Appl. 53(1), 137–143 (2007)
Gaudet, C., Maida, A.: Deep quaternion networks. In: IEEE International Joint Conference on Neural Network (IJCNN). Rio de Janeiro, Brazil (2018)
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)
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)
Gouk, H., Frank, E., Pfahringer, B., Cree, M.J.: Regularisation of neural networks by enforcing Lipschitz continuity. Mach. Learn. 110(2), 393–416 (2021)
Grassucci, E., Comminiello, D., Uncini, A.: An information-theoretic perspective on proper quaternion variational autoencoders. Entropy 23(7) (2021)
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)
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)
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
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)
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)
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)
Hoffmann, J., Schmitt, S., Osindero, S., Simonyan, K., Elsen, E.: AlgebraNets (2020). arXiv:2006.07360v2
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)
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)
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)
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)
Kingma, D.P., Welling, M.: Auto-encoding variational Bayes, pp. 1–14 (2014). arXiv:1312.6114v10
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)
Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks (2018). arXiv:1802.05957v1
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)
Parcollet, T., Morchid, M., Linarès, G.: A survey of quaternion neural networks. Art. Intell. Rev. (2019)
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)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks (2016). arXiv:1511.06434v2
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)
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)
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)
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)
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)
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)
Vìa, J., Ramìrez, D., Santamarìa, I.: Proper and widely linear processing of quaternion random vectors. IEEE Trans. Inf. Theory 56(7), 3502–3515 (2010)
Ward, J.P.: Quaternions and Cayley Numbers. Algebra and Applications. Mathematics and Its Applications, vol. 403. Kluwer Academic Publishers, Dordrecht (1997)
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)
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)
Zhang, H., Zhang, Z., Odena, A., Lee, H.: Consistency regularization for generative adversarial networks. In: International Conference on Machine Learning (ICML) (2020)
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)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
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
DOI: https://doi.org/10.1007/978-3-030-91390-8_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-91389-2
Online ISBN: 978-3-030-91390-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)