Fast and High-resolution Image Generation Based on Improved DCGAN

Yixuan Xin

doi:10.62051/2hxm5851

Authors

Yixuan Xin

DOI:

https://doi.org/10.62051/2hxm5851

Keywords:

Deep Convolution Generative Adversarial Networks; label smoothing; image generation.

Abstract

Among generative models, Generative Adversarial Network (GAN) has been sought after by researchers since its proposal. The researching fields of image generation, style transformation, data augmentation, super-resolution, image restoration, and image transformation have shined because of GAN. Deep Convolution Generative Adversarial Network (DCGAN), as an early neural network to improve GAN, solved the problem of unstableness during training. It can be easily scaled to deal with larger datasets and more sophisticated tasks, so various image generation and manipulation tasks can be tackled by this powerful tool. Nevertheless, it still has certain problems. This research investigates the hyperparameters, label smoothing and improved model’s effect on the quality and speed of image generation, and finally selects the appropriate hyperparameters and label smoothing to cooperate with the improved model to quickly generate clearer images with DCGAN in the case of few samples and few number of trainings. This work can bring some ideas for saving computational resources and data for training.

Downloads

Download data is not yet available.

References

Goodfellow, Ian, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. Advances in neural information processing systems, 2014, 27: 1-9.

Schmidhuber, Jürgen. Making the world differentiable: on using self-supervised fully recurrent neural networks for dynamic reinforcement learning and planning in non-stationary environments. Inst. für Informatik, 1990, 126. DOI: https://doi.org/10.1109/IJCNN.1990.137723

Schmidhuber, Jürgen. Learning factorial codes by predictability minimization. Neural computation, 1992, 4(6): 863-879. DOI: https://doi.org/10.1162/neco.1992.4.6.863

Liu, Bingqi, Jiwei Lv, Xinyue Fan, Jie Luo, and Tianyi Zou. Application of an improved dcgan for image generation. Mobile Information Systems, 2022: 1-14. DOI: https://doi.org/10.1155/2022/9005552

Zhu, Jun-Yan, Taesung Park, Phillip Isola, and Alexei A. Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, 2017: 2223-2232. DOI: https://doi.org/10.1109/ICCV.2017.244

Zhao, Shengyu, Zhijian Liu, Ji Lin, Jun-Yan Zhu, and Song Han. Differentiable augmentation for data-efficient gan training. Advances in neural information processing systems, 2020, 33: 7559-7570.

Ledig, Christian, Lucas Theis, Ferenc Huszár, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken et al. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2017: 4681-4690. DOI: https://doi.org/10.1109/CVPR.2017.19

Liu, Guilin, Fitsum A. Reda, Kevin J. Shih, Ting-Chun Wang, Andrew Tao, and Bryan Catanzaro. Image inpainting for irregular holes using partial convolutions. In Proceedings of the European conference on computer vision, 2018: 85-100. DOI: https://doi.org/10.1007/978-3-030-01252-6_6

Choi, Yunjey, Minje Choi, Munyoung Kim, Jung-Woo Ha, Sunghun Kim, and Jaegul Choo. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2018: 8789-8797. DOI: https://doi.org/10.1109/CVPR.2018.00916

Radford, Alec, Luke Metz, and Soumith Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks. ArXiv Preprint, 2015: 1511.06434.

Curtó, Joachim D., Irene C. Zarza, Fernando De La Torre, Irwin King, and Michael R. Lyu. High-resolution deep convolutional generative adversarial networks. ArXiv Preprint, 2017: 1711.06491.

Sun, Kun, Liangqiong Qu, Chunfeng Lian, Yongsheng Pan, Dan Hu, Bingqing Xia, Xinyue Li, Weimin Chai, Fuhua Yan, and Dinggang Shen. High-Resolution Breast MRI Reconstruction Using a Deep Convolutional Generative Adversarial Network. Journal of Magnetic Resonance Imaging, 2020, 52(6): 1852-1858. DOI: https://doi.org/10.1002/jmri.27256

Song, Yiheng, Yang Li, Yanhua Wang, and Cheng Hu. Data augmentation for imbalanced HRRP recognition using deep convolutional generative adversarial network. IEEE Access, 2020, 8: 201686-201695. DOI: https://doi.org/10.1109/ACCESS.2020.3032580

Müller, Rafael, Simon Kornblith, and Geoffrey E. Hinton. When does label smoothing help?. Advances in neural information processing systems, 2019, 32: 1-10.

A collection of high-quality anime faces. URL: https://github.com/Mckinsey666/Anime-Face-Dataset. Last Accessed: 20204/03/14