Abstract
In this paper, we propose a Self-attention StarGAN by introducing the self-attention mechanism into StarGAN to deal with multi-domain image-to-image translation, aiming to generate images with high-quality details and obtain consistent backgrounds. The self-attention mechanism models the long-range dependencies among the feature maps at all positions, which is not limited to the local image regions. Simultaneously, we take the advantage of batch normalization to reduce reconstruction error and generate fine-grained texture details. We adopt spectral normalization in the network to stabilize the training of Self-attention StarGAN. Both quantitative and qualitative experiments on a public dataset have been conducted. The experimental results demonstrate that the proposed model achieves lower reconstruction error and generates images in higher quality compared to StarGAN. We exploit Amazon Mechanical Turk (AMT) for perceptual evaluation, and 68.1% of all 1,000 AMT Turkers agree that the backgrounds of the images generated by Self-attention StarGAN are more consistent with the original images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Mao, X., Li, Q., Xie, H., Lau, R.Y.K., Wang, Z., Smolley, S.P.: On the effectiveness of least squares generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. (2018). https://doi.org/10.1109/tpami.2018.2872043
Kim, T., Cha, M., Kim, H., Lee, J.K., Kim, J.: Learning to discover cross-domain relations with generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning (ICML), pp. 1857–1865 (2017)
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR (2017). https://doi.org/10.1109/cvpr.2017.19
Shen, W., Liu, R.: Learning residual images for face attribute manipulation. In: CVPR (2017). https://doi.org/10.1109/cvpr.2017.135
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017). https://doi.org/10.1109/cvpr.2017.632
Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. In: International Conference on Learning Representations (2018)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017). https://doi.org/10.1109/iccv.2017.244
Yi, Z., Zhang, H., Tan, P., Gong, M.: DualGAN: unsupervised dual learning for image-to-image translation. In: ICCV (2017). https://doi.org/10.1109/iccv.2017.310
Li, M., Zuo, W., Zhang, D.: Deep identity-aware transfer of facial attributes. In: Computer Vision and Pattern Recognition (CVPR) (2016)
Perarnau, G., Van De Weijer, J., Raducanu, B., Álvarez, J.M.: Invertible conditional GANs for image editing. In: Computer Vision and Pattern Recognition (CVPR) (2016)
Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: Computer Vision and Pattern Recognition (CVPR) (2018). https://doi.org/10.1109/cvpr.2018.00916
Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: Machine Learning (2018)
Fu, J., Liu, J., Tian, H., Fang, Z., Lu, H.: Dual attention network for scene segmentation. In: Computer Vision and Pattern Recognition (CVPR) (2019)
Mao, X., Li, Q., Xie, H., Lau, R.Y.K., Wang, Z.: Least squares generative adversarial networks. In: ICCV (2017). https://doi.org/10.1109/iccv.2017.304
Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: ICCV (2015). https://doi.org/10.1109/iccv.2015.425
Acknowledgment
This work is supported by the National Natural Science Foundation of China (No. 61703109, No. 91748107, No. 61876065), the Guangdong Innovative Research Team Program (No. 2014ZT05G157), Natural Science Foundation of Guangdong Province, China (No. 2018A0303130022), Science and Technology Program of Guangzhou, China (No. 201904010200), and a General Research Fund (project no. 1121141) from the Research Grants Council of the Hong Kong Special Administrative Region, China.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
He, Z., Yang, Z., Mao, X., Lv, J., Li, Q., Liu, W. (2019). Self-attention StarGAN for Multi-domain Image-to-Image Translation. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Image Processing. ICANN 2019. Lecture Notes in Computer Science(), vol 11729. Springer, Cham. https://doi.org/10.1007/978-3-030-30508-6_43
Download citation
DOI: https://doi.org/10.1007/978-3-030-30508-6_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30507-9
Online ISBN: 978-3-030-30508-6
eBook Packages: Computer ScienceComputer Science (R0)