Abstract
Unsupervised image-to-image translation such as CycleGAN has received considerable attention in recent research. However, when handling large images, the quality of generated images are not in good quality. Progressive Growing GAN has proved that progressively growing of GANs could generate high pixels images. However, if we simply combine PG-method and CycleGAN, it must bring model collapse. In this paper, motivated from skip connection, we propose Progressive Growing CycleGAN (PG-Att-CycleGAN), which can stably grow the input size of both the generator and discriminator progressively from \(256\times 256\) to \(512\times 512\) and finally \(1024\times 1024\) using the weight \({\alpha }\). The whole process makes generated images clearer and stabilizes training of the network. In addition, our new generator and discriminator cannot only make the domain transfer more natural, but also increase the stability of training by using the attention block. Finally, through our model, we can process high scale images with good qualities. We use VGG16 network to evaluate domain transfer ability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017)
Pecina, P., et al.: Adaptation of machine translation for multilingual information retrieval in the medical domain. Artif. Intell. Med. 61(3), 165–185 (2014)
Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridge domain gap for person re-identification. In: CVPR (2018)
Bansal, A., Ma, S., Ramanan, D., Sheikh, Y.: Recycle-GAN: unsupervised video retargeting. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 122–138. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01228-1_8
Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability and variation. In: ICLR (2018)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Mejjati, Y.A., Richardt, C., Tompkin, J., Cosker, D.: Unsupervised attention-guided image-to-image translation. In: NIPS (2018)
Odena, A., Dumoulin, V., Olah, C.: Deconvolution and checkerboard artifacts. Distill 1, e3 (2016)
Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual Losses for Real-Time Style Transfer and Super-Resolution. arXiv preprint arXiv:1603.08155 (2016)
Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: the missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)
Zhang, H., et al.: StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks. arXiv preprint arXiv:1612.03242 (2016)
Long, J., Shelhamer, E.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)
Bellman, R., Kashef, B., Vasudevan, R.: Dynamic programming and bicubic spline interpolation. J. Math. Anal. Appl. 44, 160–174 (1973)
Wang, F., et al.: Residual Attention Network for Image Classification. arXiv preprint arXiv:1704.06904 (2017)
Kim, T., Cha, M., Kim, H., Lee, J.K., Kim, J.: Learning to discover cross-domain relations with generative adversarial networks. In: International Conference on Machine Learning (2017)
Mao, X., et al.: Least Squares Generative Adversarial Networks. arXiv preprint arXiv:1611.04076 (2016)
Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)
Arjovsky, M., Chinatala, S., Bottou, L.: Wassertein GAN. arXiv preprint arXiv:1701.07875 (2017)
Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556 (2016)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wu, Y., Zhang, R., Yanai, K. (2020). Attention Guided Unsupervised Image-to-Image Translation with Progressively Growing Strategy. In: Cree, M., Huang, F., Yuan, J., Yan, W. (eds) Pattern Recognition. ACPR 2019. Communications in Computer and Information Science, vol 1180. Springer, Singapore. https://doi.org/10.1007/978-981-15-3651-9_9
Download citation
DOI: https://doi.org/10.1007/978-981-15-3651-9_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3650-2
Online ISBN: 978-981-15-3651-9
eBook Packages: Computer ScienceComputer Science (R0)