Understanding Generative Adversarial Networks (GANs): A Review

Purwono Purwono, Annastasya Nabila Elsa Wulandari, Alfian Ma'arif, Wael A. Salah

https://ejournal.csol.or.id/public/journals/2/cover_article_170_en_US.png

Abstract


Generative Adversarial Networks (GANs) is an important breakthrough in artificial intelligence that uses two neural networks, a generator and a discriminator, that work in an adversarial framework. The generator generates synthetic data, while the discriminator evaluates the authenticity of the data. This dynamic interaction forms a minimax game that produces high-quality synthetic data. Since its introduction in 2014 by Ian Goodfellow, GAN has evolved through various innovative architectures, including Vanilla GAN, Conditional GAN (cGAN), Deep Convolutional GAN (DCGAN), CycleGAN, StyleGAN, Wasserstein GAN (WGAN), and BigGAN. Each of these architectures presents a novel approach to address technical challenges such as training stability, data diversification, and result quality. GANs have been widely applied in various sectors. In healthcare, GANs are used to generate synthetic medical images that support diagnostic development without violating patient privacy. In the media and entertainment industry, GANs facilitate the enhancement of image and video resolution, as well as the creation of realistic content. However, the development of GANs faces challenges such as mode collapse, training instability, and inadequate quality evaluation. In addition to technical challenges, GANs raise ethical issues, such as the misuse of the technology for deepfake creation. Legal regulations, detection tools, and public education are important mitigation measures. Future trends suggest that GANs will be increasingly used in text-to-image synthesis, realistic video generation, and integration with multimodal systems to support cross-disciplinary innovation.

Keywords


Generative Adversarial Networks (GANs), Mode Collapse, Deepfake, Synthetic Data, Training Stability

Full Text:

PDF

References


S. Ran, “Applications and challenges of GAN in AI-powered artistry,” Applied and Computational Engineering, vol. 41, no. 1, pp. 75–79, 2024, https://doi.org/10.54254/2755-2721/41/20230713.

M. Megahed and A. Mohammed, "Collaborative-GAN: An Approach for Stabilizing the Training Process of Generative Adversarial Network," IEEE Access, vol. 12, pp. 138716-138735, 2024, https://doi.org/10.1109/ACCESS.2024.3457902.

I. H. Rather and S. Kumar, “Generative adversarial network based synthetic data training model for lightweight convolutional neural networks,” Multimedia Tools and Applications, vol. 83, no. 2, pp. 6249–6271, 2024, https://doi.org/10.1007/s11042-023-15747-6.

R. Wang et al., “Applications of generative adversarial networks in neuroimaging and clinical neuroscience,” Neuroimage, vol. 269, p. 119898, 2023, https://doi.org/10.1016/j.neuroimage.2023.119898.

M. R. Pavan Kumar and P. Jayagopal, “Generative adversarial networks: a survey on applications and challenges,” International Journal of Multimedia Information Retrieval, vol. 10, no. 1, pp. 1–24, 2021, https://doi.org/10.1007/s13735-020-00196-w.

J. Singh, S. M. N. Islam, M. Tewatia, D. Garg and N. Fatima, "Systematic Review of GAN for Enhancing Efficiency in AI in Gaming," 2024 International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET), pp. 1-8, 2024, https://doi.org/10.1109/ACROSET62108.2024.10743943.

Y. Gong, Z. Xie, G. Duan, Z. Ma, and M. Xie, “Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networks,” Journal of Electronic Imaging, vol. 34, no. 2, p. 043029, 2022, https://doi.org/10.1117/1.JEI.32.4.043029.

M. Fathallah, M. Sakr and S. Eletriby, "Stabilizing and Improving Training of Generative Adversarial Networks Through Identity Blocks and Modified Loss Function," IEEE Access, vol. 11, pp. 43276-43285, 2023, https://doi.org/10.1109/ACCESS.2023.3272032.

Y. Gautham, S. R., and J. J., “Review on Detection Of Deepfake In Images And Videos,” International Journal of Computer Applications, vol. 186, no. 29, pp. 51–60, 2024, https://doi.org/10.5120/ijca2024923825.

Q. Li, Y. Tang, and L. Chu, “Generative adversarial networks for prognostic and health management of industrial systems: A review,” Expert Systems with Applications, vol. 253, p. 124341, 2024, https://doi.org/10.1016/j.eswa.2024.124341.

S. Azahad and S. Hameeda, “A Deep Exposition of GAN and its applications,” International Journal of Engineering Technology and Management Sciences, vol. 7, no. 2, pp. 32–37, 2023, https://doi.org/10.46647/ijetms.2023.v07i02.005.

A. Aggarwal, M. Mittal, G. Battineni, “Generative adversarial network: An overview of theory and applications,” International Journal of Information Management Data Insights, vol. 1, no. 1, p. 100004, 2021, https://doi.org/10.1016/j.jjimei.2020.100004.

Y. Benny, T. Galanti, S. Benaim, and L. Wolf, “Evaluation Metrics for Conditional Image Generation,” International Journal of Computer Vision, vol. 129, no. 5, pp. 1712–1731, 2021, https://doi.org/10.1007/s11263-020-01424-w.

M. Alfarra, J. C. Pérez, A. Frühstück, P. H. S. Torr, P. Wonka, and B. Ghanem, “On the Robustness of Quality Measures for GANs,” Computer Vision – ECCV 2022, pp. 18-33, 2022, https://doi.org/10.1007/978-3-031-19790-1_2.

H. Ye, L. Liang, G. Y. Li and B. -H. Juang, "Deep Learning-Based End-to-End Wireless Communication Systems With Conditional GANs as Unknown Channels," IEEE Transactions on Wireless Communications, vol. 19, no. 5, pp. 3133-3143, 2020, https://doi.org/10.1109/TWC.2020.2970707.

F. Ait Aoudia and J. Hoydis, "End-to-End Learning for OFDM: From Neural Receivers to Pilotless Communication," IEEE Transactions on Wireless Communications, vol. 21, no. 2, pp. 1049-1063, 2022, https://doi.org/10.1109/TWC.2021.3101364.

S. S. Mohammed and H. G. Clarke, “Conditional image-to-image translation generative adversarial network (cGAN) for fabric defect data augmentation,” Neural Computing and Applications, vol. 36, no. 32, pp. 20231–20244, 2024, https://doi.org/10.1007/s00521-024-10179-1.

G. Hu, J. Huang, Q. Wang, J. Li, Z. Xu, and X. Huang, “Unsupervised fabric defect detection based on a deep convolutional generative adversarial network,” Textile Research Journal, vol. 90, no. 3–4, pp. 247–270, 2020, https://doi.org/10.1177/0040517519862880.

N. K. Singh and K. Raza, “Medical Image Generation using Generative Adversarial Networks: A Review,” Health Informatics: A Computational Perspective in Healthcare, pp. 77-96, 2020, https://doi.org/10.1007/978-981-15-9735-0_5.

M. Lupo Pasini, V. Gabbi, J. Yin, S. Perotto, and N. Laanait, “Scalable balanced training of conditional generative adversarial neural networks on image data,” The Journal of Supercomputing, vol. 77, no. 11, pp. 13358–13384, 2021, https://doi.org/10.1007/s11227-021-03808-2.

S. Li, “The study for optimization strategies on the performance of DCGAN,” Journal of Physics: Conference Series, vol. 2634, no. 1, p. 012032, 2023, https://doi.org/10.1088/1742-6596/2634/1/012032.

A. Radford, L. Metz, and S. Chintala, “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,” arXiv, 2015, https://doi.org/10.48550/arXiv.1511.06434.

L. Krstanović, B. Popović, M. Janev, and B. Brkljač, “Feature Map Regularized CycleGAN for Domain Transfer,” Mathematics, vol. 11, no. 2, p. 372, 2023, https://doi.org/10.3390/math11020372.

C.-T. Tu, H. J. Lin, and Y. Tsia, “Multi-style image transfer system using conditional cycleGAN,” The Imaging Science Journal, vol. 69, no. 1–4, pp. 1–14, 2021, https://doi.org/10.1080/13682199.2020.1759977.

C. Wan et al., “Retinal Image Enhancement Using Cycle-Constraint Adversarial Network,” Frontiers in Medicine, vol. 8, 2022, https://doi.org/10.3389/fmed.2021.793726.

J. Peng, K. Chen, Y. Gong, T. Zhang, and B. Su, “Cyclic Consistent Image Style Transformation: From Model to System,” Applied Sciences, vol. 14, no. 17, p. 7637, 2024, https://doi.org/10.3390/app14177637.

T. K. Yoo, J. Y. Choi, and H. K. Kim, “CycleGAN-based deep learning technique for artifact reduction in fundus photography,” Graefe’s Archive for Clinical and Experimental Ophthalmology, vol. 258, no. 8, pp. 1631–1637, 2020, https://doi.org/10.1007/s00417-020-04709-5.

R. Abdal, P. Zhu, N. Mitra, and P. Wonka, “StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows,” ACM Transactions on Graphics, vol. 40, no. 3, pp. 1-21, 2020, https://doi.org/10.1145/3447648.

J. N. M. Pinkney and D. Adler, “Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domains,” arXiv, 2020, https://doi.org/10.48550/arXiv.2010.05334.

T. Karmali et al., “Hierarchical Semantic Regularization of Latent Spaces in StyleGANs,” Computer Vision – ECCV 2022, pp. 443–459, 2022, https://doi.org/10.1007/978-3-031-19784-0_26.

T. Karras, S. Laine and T. Aila, "A Style-Based Generator Architecture for Generative Adversarial Networks," 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4396-4405, 2019, https://doi.org/10.1109/CVPR.2019.00453.

K. Hiraide, K. Hirayama, K. Endo, and M. Muramatsu, “Application of deep learning to inverse design of phase separation structure in polymer alloy,” Computational Materials Science, vol. 190, p. 110278, 2021, https://doi.org/10.1016/j.commatsci.2021.110278.

J. Gao, “A comparative study between WGAN-GP and WGAN-CP for image generation,” Applied and Computational Engineering, vol. 83, no. 1, pp. 15–19, 2024, https://doi.org/10.54254/2755-2721/83/2024GLG0059.

S. Han, A. Srivastava, C. Hurwitz, P. Sattigeri, and D. D. Cox, “not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution,” arXiv, 2020, https://doi.org/10.48550/arXiv.2009.04433.

M. Lee, D. Tae, J. H. Choi, H.-Y. Jung, and J. Seok, “Improved recurrent generative adversarial networks with regularization techniques and a controllable framework,” Information Sciences, vol. 538, pp. 428–443, 2020, https://doi.org/10.1016/j.ins.2020.05.116.

A. Brock, J. Donahue, and K. Simonyan, “Large Scale GAN Training for High Fidelity Natural Image Synthesis,” arXiv, 2018, https://doi.org/10.48550/arXiv.1809.11096.

D. Torbunov et al., "UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation," 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 702-712, 2023, https://doi.org/10.1109/WACV56688.2023.00077.

D. Ku and H. Park, “Improvement of SRGAN Performance Using Mutual Distillation,” Journal of Korea Multimedia Society, vol. 25, no. 12, pp. 1673–1680, 2022, https://doi.org/10.9717/kmms.2022.25.12.1673.

M. Momen-Tayefeh, M. Momen-Tayefeh, and A. A. G. Ghahramani, “Image inpainting for corrupted images by using the semi-super resolution GAN,” arXiv, 2024, https://doi.org/10.48550/arXiv.2409.12636.

F. Rahat, M. S. Hossain, M. R. Ahmed, S. K. Jha, and R. Ewetz, “Data Augmentation for Image Classification using Generative AI,” arXiv, 2024, https://doi.org/10.48550/arXiv.2409.00547.

P. Ghasemi, C. Yuan, T. Marion, and M. Moghaddam, “DCG-GAN: design concept generation with generative adversarial networks,” Design Science, vol. 10, p. e14, 2024, https://doi.org/10.1017/dsj.2024.13.

A. Biswas et al., “Generative Adversarial Networks for Data Augmentation,” Data Driven Approaches on Medical Imaging, pp. 159–177, 2023, https://doi.org/10.1007/978-3-031-47772-0_8.

O. Fedoruk, K. Klimaszewski, A. Ogonowski, and R. Możdżonek, “Performance of GAN-based augmentation for deep learning COVID-19 image classification,” AIP Conference Proceedings, vol. 3061, no. 1, p. 030001, 2023, https://doi.org/10.1063/5.0203379.

K. Xie et al., “GAN‐based metal artifacts region inpainting in brain MRI imaging with reflective registration,” Medical Physics, vol. 51, no. 3, pp. 2066–2080, 2024, https://doi.org/10.1002/mp.16724.

A. Aghelan and M. Rouhani, “Fine-tuned Generative Adversarial Network-based Model for Medical Image Super-Resolution,” arXiv, 2022, https://doi.org/10.48550/arXiv.2211.00577.

L. Wyse, P. Kamath, and C. Gupta, “Sound Model Factory: An Integrated System Architecture for Generative Audio Modelling,” Artificial Intelligence in Music, Sound, Art and Design, pp. 308-322, 2022, https://doi.org/10.1007/978-3-031-03789-4_20.

S. Kar, “Study of Generative Adversarial Networks for Acoustic Signal Enhancement: A Review,” International Journal of Emerging Trends in Engineering Research, vol. 10, no. 9, pp. 406–413, 2022, https://doi.org/10.30534/ijeter/2022/011092022.

N. Kaur and P. Tuttosi, “Time out of Mind: Generating Rate of Speech conditioned on emotion and speaker,” arXiv, 2023, https://doi.org/10.48550/arXiv.2301.12331.

Z. Yang, “A review of motion generation technology,” Applied and Computational Engineering, vol. 30, no. 1, pp. 68–73, 2024, https://doi.org/10.54254/2755-2721/30/20230073.

A. Maity, R. Pious, S. K. Lenka, V. Choudhary, and S. Lokhande, “A Survey on Super Resolution for video Enhancement Using GAN,” arXiv, 2023, https://doi.org/10.48550/arXiv.2312.16471.

A. Mittal, B. Kaur and N. Kaur, "Enhancing Video Frame Interpolation using Modified GAN Architecture: A Deep Learning Approach," 2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS), pp. 1-5, 2024, https://doi.org/10.1109/IACIS61494.2024.10721736.

C. Yuan, T. Marion, and M. Moghaddam, “DDE-GAN: Integrating a Data-Driven Design Evaluator Into Generative Adversarial Networks for Desirable and Diverse Concept Generation,” Journal of Mechanical Design, vol. 145, no. 4, p. 041407, 2023, https://doi.org/10.1115/1.4056500.

M. Arifin, S. Ahmed, T. Kumar Ghosh, J. Zhuang, and J.-H. Yeh, “A Survey on the Application of Generative Adversarial Networks in Cybersecurity: Prospective, Direction and Open Research Scopes,” arXiv, 2024, https://doi.org/10.48550/arXiv.2407.08839.

A. Jafari, A. Al-Mousa, and I. Jafar, “Speaker anonymization using generative adversarial networks,” Journal of Intelligent & Fuzzy Systems, vol. 45, no. 2, pp. 3345–3359, 2023, https://doi.org/10.3233/JIFS-223642.

M.-S. Yu et al., “A Variational Autoencoder Cascade Generative Adversarial Network for Scalable 3D Object Generation and Reconstruction,” Sensors, vol. 24, no. 3, p. 751, 2024, https://doi.org/10.3390/s24030751.

A. Ayala, C. Drazic, B. Hutchinson, B. Kravitz, and C. Tebaldi, “Loosely Conditioned Emulation of Global Climate Models With Generative Adversarial Networks,” arXiv, 2021, https://doi.org/10.48550/arXiv.2105.06386.

Z. Dai, L. Zhao, K. Wang, and Y. Zhou, “Mode standardization: A practical countermeasure against mode collapse of GAN-based signal synthesis,” Applied Soft Computing, vol. 150, p. 111089, 2024, https://doi.org/10.1016/j.asoc.2023.111089.

D. Wang, X. Qin, F. Song and L. Cheng, "Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent," IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 7, pp. 2768-2780, 2022, https://doi.org/10.1109/TNNLS.2020.3045082.

Y. Ni, “Enhancing the stability of Generative Adversarial Networks: A survey of progress and techniques,” Applied and Computational Engineering, vol. 74, no. 1, pp. 21–26, 2024, https://doi.org/10.54254/2755-2721/74/20240427.

B. Farhadinia, M. R. Ahangari, A. Heydari, and A. Datta, “A generalized optimization-based generative adversarial network,” Expert Systems with Applications, vol. 248, p. 123413, 2024, https://doi.org/10.1016/j.eswa.2024.123413.

M. M. Saad, M. H. Rehmani, and R. O’Reilly, “Assessing Intra-class Diversity and Quality of Synthetically Generated Images in a Biomedical and Non-biomedical Setting,” arXiv, 2023, https://doi.org/10.48550/arXiv.2308.02505.

F. L. Barsha and W. Eberle, “Mode Collapse Detection Strategies in Generative Adversarial Networks for Credit Card Fraud Detection,” The International FLAIRS Conference Proceedings, vol. 37, no. 1, 2024, https://doi.org/10.32473/flairs.37.1.135493.

Z. Shi, J. Li, and Y. You, “ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networks,” SoCC '24: Proceedings of the 2024 ACM Symposium on Cloud Computing, pp. 1032 –1044, 2024, https://doi.org/10.1145/3698038.3698563.

Z. Polizzi and C.-Y. Tsai, “FusedProp: Towards Efficient Training of Generative Adversarial Networks,” arXiv, 2020, https://doi.org/10.48550/arXiv.2004.03335.

Y. Zhao, C. Li, P. Yu, J. Gao, and C. Chen, “Feature Quantization Improves GAN Training,” arXiv, 2020, https://doi.org/10.48550/arXiv.2004.02088.

S. Wang, T. Tricco, X. Jiang, C. Robertson, and J. Hawkin, “Synthetic Demographic Data Generation for Card Fraud Detection Using GANs,” arXiv. 2023, https://doi.org/10.48550/arXiv.2306.17109.

A. Alshantti, A. Rasheed, and F. Westad, “Privacy Re‐Identification Attacks on Tabular GANs,” Security and Privacy, vol. 8, no. 1, p. e469, 2025, https://doi.org/10.1002/spy2.469.

Z. Lin, V. Sekar, and G. Fanti, “Why Spectral Normalization Stabilizes GANs: Analysis and Improvements,” arXiv, 2020, https://doi.org/10.48550/arXiv.2009.02773.

A. K. Mondal, V. Jain, and K. Siddiqi, “Mini-batch graphs for robust image classification,” arXiv, 2021, https://doi.org/10.48550/arXiv.2105.03237.

T. Ma and W. Tian, “Back-projection-based progressive growing generative adversarial network for single image super-resolution,” The Visual Computer, vol. 37, no. 5, pp. 925–938, 2021, https://doi.org/10.1007/s00371-020-01843-3.

M. L. Pasini, V. Gabbi, J. Yin, S. Perotto, and N. Laanait, “Scalable balanced training of conditional generative adversarial neural networks on image data,” The Journal of Supercomputing, vol. 77, no. 11, pp. 13358–13384, 2021, https://doi.org/10.1007/s11227-021-03808-2.

M. M. Saad, M. H. Rehmani, and R. O’Reilly, “A Self-attention Guided Multi-scale Gradient GAN for Diversified X-ray Image Synthesis,” Artificial Intelligence and Cognitive Science, pp. 18-31, 2022, https://doi.org/10.1007/978-3-031-26438-2_2.

A. Kumar et al., "CoroNetGAN: Controlled Pruning of GANs via Hypernetworks," 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 1254-1263, 2023, https://doi.org/10.1109/ICCVW60793.2023.00136.

P. Andreev, A. Fritzler, and D. Vetrov, “Quantization of Generative Adversarial Networks for Efficient Inference: a Methodological Study,” arXiv, 2021, https://doi.org/10.48550/arXiv.2108.13996.

T. Shimizu, J. Xu, and K. Tasaka, “MobileGAN: Compact Network Architecture for Generative Adversarial Network,” Pattern Recognition, pp. 326–338, 2020, https://doi.org/10.1007/978-3-030-41404-7_23.

C. Shi, Y. Hao, G. Li, and S. Xu, “Knowledge distillation via Noisy Feature Reconstruction,” Expert Systems with Applications, vol. 257, p. 124837, 2024, https://doi.org/10.1016/j.eswa.2024.124837.




DOI: https://doi.org/10.59247/csol.v3i1.170

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 Purwono Purwono

 
Control Systems and Optimization Letters
ISSN: 2985-6116
Website: https://ejournal.csol.or.id/index.php/csol
Email: alfian_maarif@ieee.org
Publisher: Peneliti Teknologi Teknik Indonesia
Address: Jl. Empu Sedah No. 12, Pringwulung, Condongcatur, Kec. Depok, Kabupaten Sleman, Daerah Istimewa Yogyakarta 55281, Indonesia