Abstract
We propose a systematic analysis of the neglected spectral bias in the frequency domain in this paper. Traditional generative adversarial networks (GANs) try to fulfill the details of images by designing specific network architectures or losses, focusing on generating visually qualitative images. The convolution theorem shows that image processing in the frequency domain is parallelizable and performs better and faster than that in the spatial domain. However, there is little work about discussing the bias of frequency features between the generated images and the real ones. In this paper, we first empirically demonstrate the general distribution bias across datasets and GANs with different sampling methods. Then, we explain the causes of the spectral bias through the deduction that reconsiders the sampling process of the GAN generator. Based on these studies, we provide a low-spectral-bias hybrid generative model to reduce the spectral bias and improve the quality of the generated images.
This work is supported in part by the National Key Research and Development Program of China under Grant no. 2020YFB1806403.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Khayatkhoei, M., Singh, M.K., Elgammal, A.: Disconnected manifold learning for generative adversarial networks. In: Advances in Neural Information Processing Systems, pp. 7343–7353 (2018)
Zhang, D., Zuo, W., Zhang, D., Zhang, H.: Time series classification using support vector machine with Gaussian elastic metric kernel. In: 2010 20th International Conference on Pattern Recognition, pp. 29–32. IEEE (2010)
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)
Rahaman, N., et al.: On the spectral bias of neural networks. In: International Conference on Machine Learning, pp. 5301–5310. PMLR (2019)
Zhang, D., Lin, L., Chen, T., Wu, X., Tan, W., Izquierdo, E.: Content-adaptive sketch portrait generation by decompositional representation learning. IEEE Trans. Image Process. 26(1), 328–339 (2016)
Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans. Image Process. 26(7), 3142–3155 (2017)
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein GANs. In: Advances in Neural Information Processing Systems, pp. 5767–5777 (2017)
Choi, Y., Choi, M., Kim, M., Ha, J.-W., Kim, S., Choo, J.: StarGAN: Unified generative adversarial networks for multidomain image-to-image translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8789–8797 (2018)
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: Advances in Neural Information Processing Systems, pp. 6626–6637 (2017)
Durall, R., Keuper, M., Keuper, J.: Watch your upconvolution: CNN based generative deep neural networks are failing to reproduce spectral distributions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7890–7899 (2020)
Odena, A., Dumoulin, V., Olah, C.: Deconvolution and checkerboard artifacts. Distill (2016). http://distill.pub/2016/deconv-checkerboard
Wang, H., Wu, X., Huang, Z., Xing, E.P.: High-frequency component helps explain the generalization of convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8684–8694 (2020)
Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)
Chen, X., Gupta, A.: An implementation of faster RCNN with study for region sampling. arXiv preprint arXiv:1702.02138 (2017)
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)
Zhang, W., Sun, J., Tang, X.: Cat head detection - how to effectively exploit shape and texture features. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5305, pp. 802–816. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-88693-8_59
Baddeley, R.: The correlational structure of natural images and the calibration of spatial representations. Cogn. Sci. 21(3), 351–372 (1997)
Jolicoeur-Martineau, A.: The relativistic discriminator: a key element missing from standard GAN. arXiv preprint arXiv:1807.00734 (2018)
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 Singapore Pte Ltd.
About this paper
Cite this paper
Xu, L., Liu, Z., Liu, P., Cai, L. (2022). A Low Spectral Bias Generative Adversarial Model for Image Generation. In: Wang, Y., Zhu, G., Han, Q., Wang, H., Song, X., Lu, Z. (eds) Data Science. ICPCSEE 2022. Communications in Computer and Information Science, vol 1628. Springer, Singapore. https://doi.org/10.1007/978-981-19-5194-7_26
Download citation
DOI: https://doi.org/10.1007/978-981-19-5194-7_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-5193-0
Online ISBN: 978-981-19-5194-7
eBook Packages: Computer ScienceComputer Science (R0)