• Nguyen Mau Truong Giang VNPT – AI
  • Van-Hau Nguyen Hung Yen University of Technology and Education
Keywords: Generative Adversarial Networks (GANs), Generative models, Evaluation metrics, Model stability, Loss functions, Machine Learning Applications


This study presents a comprehensive analysis of Generative Adversarial Networks (GANs), focusing on their transformative role since their inception in 2014. Emphasizing game-theoretical principles, GANs mark a significant shift in generative modeling, predominantly applied in diverse fields from computer vision to data science. Our research rigorously investigates the evolutionary advancements in GAN architectures and evaluation metrics, particularly addressing the enhancement of data quality and the resolution of training instabilities. We delve into various GAN derivatives, including Conditional GANs, Wasserstein GANs, CycleGANs, and StyleGANs, exploring their unique contributions to improved modeling performance. This paper highlights the extensive applications of these models and their impact in practical scenarios. Additionally, we address current challenges within the GAN domain and suggest potential future research directions. Our work provides a concise yet comprehensive overview of GAN frameworks, underscoring their ongoing evolution and relevance in modern machine learning.


I.Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative Adversarial Networks” (advances in neural information processing systems)”, Red Hook, NY Curran, 2014, pp. 2672–2680.

M. Mirza and S. Osindero, “Conditional generative adversarial nets,” arXiv preprint arXiv:1411.1784, 2014.

Martin Arjovsky, Soumith Chintala, Léon Bottou, “Wasserstein GAN,” arXiv preprint arXiv: 1701.07875v3, 2017.

H. Zhang, T. Xu, H. Li, S. Zhang, X. Wang, X. Huang, and D. N.Metaxas, “Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 5907–5915.

T. Karras, T. Aila, S. Laine, and J. Lehtinen, “Progressive growing of gans for improved quality, stability, and variation,” arXiv preprint arXiv:1710.10196, 2017.

T. Karras, S. Laine, and T. Aila, “A style-based generator architecture for generative adversarial networks,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp.4401–4410.

Alec Radford, Luke Metz, Soumith Chintala, “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,” arXiv preprint arXiv: 1511.06434, 2015.

X. Chen, Y. Duan, R. Houthooft, J. Schulman, I. Sutskever, and P. Abbeel, “Infogan: Interpretable representation learning by information maximizing generative adversarial nets,” Advances in neural information processing systems, 2016, vol. 29.

Xudong Mao, Qing Li, Haoran Xie, Raymond Y.K. Lau, Zhen Wang, Stephen Paul Smolley, “Least Squares Generative Adversarial Networks,” arXiv preprint arXiv: 1611.04076, 2016.

Jun-Yan Zhu, Taesung Park, Phillip Isola, “Unpaired Image-to-Image Translation using Cycle Consistent Adversarial Networks,” arXiv preprint arXiv: 1703.10593, 2017.

Andrew Brock, Jeff Donahue, Karen Simonyan, “Large Scale GAN Training for High Fidelity Natural Image Synthesis,” arXiv preprint arXiv: 1809.11096, 2018.

Taesung Park, Ming-Yu Liu, Ting-Chun Wang, Jun-Yan Zhu, “A Style-Based Generator Architecture for Generative Adversarial Networks,” arXiv preprint arXiv: 1812.04948, 2018.

Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena, “Semantic Image Synthesis with Spatially-Adaptive Normalization,” arXiv preprint arXiv: 1903.07291, 2019.

Edgar Schönfeld, Bernt Schiele, Anna Khoreva, “A U-Net Based Discriminator for Generative Adversarial Networks,” arXiv preprint arXiv: 2002.12655, 2020.

Stanislav Pidhorskyi, Donald Adjeroh, Gianfranco Doretto, “Adversarial Latent Autoencoders,” arXiv preprint arXiv: 2004.04467, 2020.

Yifan Jiang, Shiyu Chang, Zhangyang Wang, “TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up,” arXiv preprint arXiv: 2102.07074, 2021.

Zhendong Wang, Huangjie Zheng, Pengcheng He, Weizhu Chen, Mingyuan Zhou, “DiffusionGAN: Training GANs with Diffusion,” arXiv preprint arXiv: 2206.02262, 2021.

Rinon Gal, Dana Cohen, Amit Bermano, Daniel Cohen-Or, “SWAGAN: A Style-based Wavelet driven Generative Model,” arXiv preprint arXiv 2102.06108, 2021.

X. Liu, M. Cheng, H. Zhang, and C.-J. Hsieh, “Towards robust neural networks via random self-ensemble,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 369–385.

How to Cite
Nguyen Mau Truong Giang, & Van-Hau Nguyen. (2023). ADVANCEMENTS IN GAN MODELS: A STUDY OF KEY VARIANTS AND EVALUATION METRICS. UTEHY Journal of Science and Technology, 40, 8-14. Retrieved from