A Review on Comparative Analysis of Generative Adversarial Networks’ Architectures and Applications
DOI:
https://doi.org/10.18196/jrc.v6i1.24160Keywords:
Artificial Intelligence (AI), Computer Vision (CV), Deep Learning, Generative Adversarial Networks (GAN), Image Synthesis.Abstract
Generative Adversarial Networks (GANs) are a major advancement in generative modeling, surpassing traditional machine learning models in tasks such as image generation, super-resolution, and image-to-text translation. A GAN consists of two neural networks: a Generator (G), which creates data from noise or a latent vector, and a Discriminator (D), which determines whether the data is real or generated. These networks train competitively, improving each other iteratively to produce increasingly realistic outputs. However, GANs face challenges like mode collapse, unstable training, and convergence issues, leading to the adoption of strategies such as instance normalization and enhanced loss functions. Future research can focus on improving stability, developing novel loss functions, and applying GANs in unsupervised learning. Performance metrics like Inception Score, Fréchet Inception Distance (FID), and Structural Similarity Index (SSIM) are essential for evaluating and comparing GAN architectures. Additionally, ethical concerns, including the misuse of GANs for deepfakes and synthetic data, underscore the importance of transparency, accountability, and ethical standards in research and deployment. This review provides an accessible introduction to GANs for novice researchers, along with a detailed analysis of their limitations, applications, and future prospects, offering valuable insights and direction for advancing this field.
References
F. PirahanSiah, “Computer Vision, Deep Learning, Deep Reinforcement Learning,” Scienceopen, 2019, doi: 10.14293/s2199-1006.1.sor-uncat.clzwyuz.v1.
I. Goodfellow, “Generative adversarial networks,” Communications of the ACM, vol. 63, no. 11, pp. 139-144, 2020, doi: 10.1145/3422622.
R. Viñas, T. Azevedo, E. R. Gamazon, and P. Liò, “Gene Expression Imputation with Generative Adversarial Imputation Nets,” BioRxiv, 2020, doi: 10.1101/2020.06.09.141689.
U. Kamath, K. L. Graham, and W. Emara, “Bidirectional Encoder Representations from Transformers (BERT),” Transformers for Machine Learning, pp. 43-70, 2022, doi: 10.1201/9781003170082-3.
T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, and D. Amodei, "Language models are few-shot learners," in Advances in Neural Information Processing Systems, vol. 33, pp. 1877-1901, 2020.
P. Dhariwal, H. Jun, C. Payne, J. W. Kim, A. Radford, and I. Sutskever, "Jukebox: A generative model for music," arXiv preprint arXiv:2005.00341, 2020.
R. Yamamoto, E. Song, and J. -M. Kim, "Parallel Wavegan: A Fast Waveform Generation Model Based on Generative Adversarial Networks with Multi-Resolution Spectrogram," ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6199-6203, 2020, doi: 10.1109/ICASSP40776.2020.9053795.
T. Karras, M. Aittala, J. Hellsten, S. Laine, J. Lehtinen, and T. Aila, "Training Generative Adversarial Networks with limited data," in Advances in Neural Information Processing Systems, vol. 33, pp. 12104-12114, 2020.
R. Cakaj, J. Mehnert, and B. Yang, “Spectral Batch Normalization: Normalization in the Frequency Domain,” 2023 International Joint Conference on Neural Networks (IJCNN), pp. 1-10, 2023, doi: 10.1109/ijcnn54540.2023.10191931.
W. Kłos, P. Coronica, K. Seeliger, and M. N. Hebart, “Training BigGAN on an ecologically motivated image dataset,” 2022 Conference on Cognitive Computational Neuroscience, 2022, doi: 10.32470/ccn.2022.1144-0.
B. Brock, J. Donahue, and K. Simonyan, "Large Scale GAN Training for High Fidelity Natural Image Synthesis," arXiv preprint arXiv:1809.11096, 2020.
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, pp. 4401-4410, 2019.
N. Meira, M. Silva, A. Bianchi, and R. Oliveira, “Generating Synthetic Faces for Data Augmentation with StyleGAN2-ADA,” Proceedings of the 25th International Conference on Enterprise Information Systems, pp. 649-655, 2023, doi: 10.5220/0011994600003467.
S. Kumar and S. Dhawan, "A detailed study on Generative Adversarial Networks," in 2020 5th International Conference on Communication and Electronics Systems (ICCES), pp. 641-645, 2020.
V. Raj, R. Kumar, and N. Kumar, “A Scrupulous Framework to Forecast the Weather using CNN with Back Propagation Method,” 2022 4th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), vol. 8, pp. 177-181, 2022, doi: 10.1109/icac3n56670.2022.10074346.
Y. Wang, N. Polson, and V. O. Sokolov, “Data Augmentation for Bayesian Deep Learning,” Bayesian Analysis, vol. 18, no. 4, 2023, doi: 10.1214/22-ba1331.
J. Jam, C. Kendrick, V. Drouard, K. Walker, G.-S. Hsu, and M. Yap, “Symmetric Skip Connection Wasserstein GAN for High-resolution Facial Image Inpainting,” Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, pp. 35-44, 2021, doi: 10.5220/0010188700350044.
Y. Chen and X. Hou, “An Improvement based on Wasserstein GAN for Alleviating Mode Collapsing,” 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1-7, 2020, doi: 10.1109/ijcnn48605.2020.9207717.
H. Zhang, I. Goodfellow, D. Metaxas, and A. Odena, "Self-attention Generative Adversarial Networks," in Proceedings of the International Conference on Machine Learning, pp. 7354-7363, 2019.
H. Gouk, E. Frank, B. Pfahringer, and M. J. Cree, "Regularisation of neural networks by enforcing Lipschitz continuity," Machine Learning, vol. 110, pp. 393-416, 2021.
M. Ghayoumi, “Deep Convolutional Generative Adversarial Networks (DCGANs),” Generative Adversarial Networks in Practice, pp. 220-257, 2023, doi: 10.1201/9781003281344-8.
D. Pham and T. Le, “Auto-Encoding Variational Bayes for Inferring Topics and Visualization,” Proceedings of the 28th International Conference on Computational Linguistics, pp. 5223-5234, 2020, doi: 10.18653/v1/2020.coling-main.458.
V. K. Chauhan, “Stochastic Trust Region Inexact Newton Method,” Stochastic Optimization for Large-scale Machine Learning, pp. 123-138, 2021, doi: 10.1201/9781003240167-10.
C. Shi, W. Liu, J. Meng, Z. Li, and J. Liu, “Semantic-wise hybrid attention generative adversarial network for image inpainting,” Research Square, 2023, doi: 10.21203/rs.3.rs-3382745/v1.
Z. Luo, H. Yu, and Y. Zhang, “Pine Cone Detection Using Boundary Equilibrium Generative Adversarial Networks and Improved YOLOv3 Model,” Sensors, vol. 20, no. 16, p. 4430, 2020, doi: 10.3390/s20164430.
F. Ros and R. Riad, “Deep clustering techniques based on autoencoders,” Unsupervised and Semi-Supervised Learning, pp. 203-220, 2023, doi: 10.1007/978-3-031-48743-9_11.
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, 2023, doi: 10.2139/ssrn.4423104.
S. W. Park, J. H. Huh, and J. C. Kim, "BEGAN v3: avoiding mode collapse in GANs using variational inference," Electronics, vol. 9, no. 4, p. 688, 2020.
Y. Bodyanskiy, A. Deineko, V. Skorik, and F. Brodetskyi, “Deep Neural Network with Adaptive Parametric Rectified Linear Units and its Fast Learning,” International Journal of Computing, pp. 11-18, 2022, doi: 10.47839/ijc.21.1.2512.
R. Alkhatib, “Artificial Neural Network Activation Functions in Exact Analytical Form (Heaviside, ReLU, PReLU, ELU, SELU, ELiSH),” Authorea Preprints, 2021, doi: 10.36227/techrxiv.15096888.v1.
X. Li and Z. Zhang, “The comparison between Conditional Generative Adversarial Nets and Deep Convolutional Generative Adversarial Network, and its GUI-related application,” 2021 2nd International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), pp. 601-609, 2021, doi: 10.1109/icbase53849.2021.00119.
L. Nguyen, “Adversarial Variational Autoencoders to Extend and Improve Generative Model,” Computer Science and Mathematics, 2023, doi: 10.20944/preprints202308.0131.v1.
P. N. Deelaka, “Neural Artistic Style Transfer with Conditional Adversarial Network,” Available at SSRN 4358610, 2023, doi: 10.2139/ssrn.4358610.
M. Ghayoumi, “Generative Adversarial Networks (GANs) for Images,” Generative Adversarial Networks in Practice, pp. 436-477, 2023, doi: 10.1201/9781003281344-14.
M. Xu, "Towards generalized implementation of Wasserstein distance in GANs," in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 12, pp. 10514-10522, May 2021.
J. Hwang and D. Suh, “CC-GAIN: Clustering and Classification-Based Generative Adversarial Imputation Network for Missing Electricity Consumption Data Imputation,” Expert Systems with Applications, vol. 255, p. 124507 2023.
H. Alqahtani, M. Kavakli-Thorne, and G. Kumar, "Applications of generative adversarial networks (GANs): An updated review," Archives of Computational Methods in Engineering, vol. 28, pp. 525-552, 2021.
A. Karnewar and O. Wang, "MSG-GAN: Multi-scale gradients for generative adversarial networks," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7799-7808, 2020.
A. Zhavoronkov et al., "Potential non-covalent SARS-CoV-2 3C-like protease inhibitors designed using generative Deep Learning approaches and reviewed by human medicinal chemist in virtual reality," ChemRxiv, 2020.
M. Yurt, S. U. Dar, A. Erdem, E. Erdem, K. K. Oguz, and T. Çukur, "mustGAN: multi-stream generative adversarial networks for MR image synthesis," Medical Image Analysis, vol. 70, p. 101944, 2021.
A. You, J. K. Kim, I. H. Ryu, and T. K. Yoo, "Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey," Eye and Vision, vol. 9, no. 1, p. 6, 2022.
M. N. Minaidi, C. Papaioannou, and A. Potamianos, “Self-Attention Based Generative Adversarial Networks For Unsupervised Video Summarization,” 2023 31st European Signal Processing Conference (EUSIPCO), pp. 571-575, 2023, doi: 10.23919/eusipco58844.2023.10289808.
L. Zhang, Z. Xu, Y. Liu, T. Qiao, H. Su, and Y. Luo, “Transformer Fault Diagnosis Based on Adversarial Generative Networks and Deep Stacked Autoencoder,” Heliyon, vol. 10, no. 9, 2024.
H. Wang, W. Wu, Y. Su, Y. Duan, and P. Wang, "Image super-resolution using an improved generative adversarial network," in 2019 IEEE 9th International Conference on Electronics Information and Emergency Communication (ICEIEC), pp. 312-315, 2019.
X. Wang et al., "ESRGAN: Enhanced super-resolution generative adversarial networks," in Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018.
S. W. Park, J. S. Ko, J. H. Huh, and J. C. Kim, "Review on generative adversarial networks: focusing on computer vision and its applications," Electronics, vol. 10, no. 10, p. 1216, 2021.
W. Zhang, P. Zhang, Y. Yu, X. Li, S. A. Biancardo, and J. Zhang, "Missing data repairs for traffic flow with self-attention generative adversarial imputation net," IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 7, pp. 7919-7930, 2021.
D. Mahapatra and Z. Ge, "Training data independent image registration using generative adversarial networks and domain adaptation," Pattern Recognition, vol. 100, p. 107109, 2020.
K. K. Babu and S. R. Dubey, "CSGAN: Cyclic-synthesized generative adversarial networks for image-to-image transformation," Expert Systems with Applications, vol. 169, p. 114431, 2021.
M. Torabi, “SumcaVer1: Mean Square Prediction Error Estimation in Small Area Estimation,” CRAN: Contributed Packages, 2024, doi: 10.32614/cran.package.sumcaver1.
S. Talafha, B. Rekabdar, C. P. Ekenna, and C. Mousas, “Attentional Adversarial Variational Video Generation via Decomposing Motion and Content,” 2020 IEEE 14th International Conference on Semantic Computing (ICSC), pp. 45-52, 2020, doi: 10.1109/icsc.2020.00014.
D. Torbunov et al., "UVCGAN: Unet vision transformer cycle-consistent GAN for unpaired image-to-image translation," in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 702-712, 2023.
Y. J. Yeo, M. C. Sagong, S. Park, S. J. Ko, and Y. G. Shin, "Image generation with self-pixel-wise normalization," Applied Intelligence, vol. 53, no. 8, pp. 9409-9423, 2023.
C. F. Foo and S. Winkler, “Image Data Augmentation with Unpaired Image-to-Image Camera Model Translation,” 2022 IEEE International Conference on Image Processing (ICIP), pp. 3246-3250, 2022, doi: 10.1109/icip46576.2022.9897671.
R. H. Randhawa, N. Aslam, M. Alauthman, and H. Rafiq, "Evasion generative adversarial network for low data regimes," IEEE Transactions on Artificial Intelligence, vol. 4, no. 5, pp. 1076-1088, 2022.
V. Chinbat and S. H. Bae, "Ga3n: Generative adversarial autoaugment network," Pattern Recognition, vol. 127, p. 108637, 2022.
R. H. Randhawa, N. Aslam, M. Alauthman, M. Khalid, and H. Rafiq, "Deep reinforcement learning based Evasion Generative Adversarial Network for botnet detection," Future Generation Computer Systems, vol. 150, pp. 294-302, 2024.
S. Zhao, Z. Liu, J. Lin, J. Y. Zhu, and S. Han, "Differentiable augmentation for data-efficient GAN training," in Advances in Neural Information Processing Systems, vol. 33, pp. 7559-7570, 2020.
L. Cai, “Comparative Analysis the Super-Resolution Image Generation Performance Based on BigGAN and VQ-VAE-2,” Highlights in Science, Engineering and Technology, vol. 41, pp. 202-210, 2023, doi: 10.54097/hset.v41i.6812.
P. Patel, N. Kumari, M. Singh, and B. Krishnamurthy, "LT-GAN: Self-supervised GAN with latent transformation detection," in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 3189-3198, 2021.
R. Quaicoo, R. Acheampong, P. Gyamenah, A. A. Dodoo, M. A. T. Soli, and J. K. Appati, “Adapting Triple-BigGAN for Image Detection Tasks: Challenges and Opportunities,” Research Square, 2024, doi: 10.21203/rs.3.rs-4262097/v1.
S. A. Gebereselassie and B. K. Roy, “Secure Image Encryption Algorithm based on Two-Level Diffusion and Hybrid Chaotic Maps,” 2023 IEEE Silchar Subsection Conference (SILCON), pp. 1-6, 2023, doi: 10.1109/silcon59133.2023.10404972.
B. Fathi-Vajargah, “Image Encryption Based on Permutation and Substitution Using Clifford Chaotic System and Logistic Map,” Journal of Computers, pp. 309-326, 2018, doi: 10.17706/jcp.13.3.309-326.
S. Farwa, N. Muhammad, N. Bibi, S. A. Haider, S. R. Naqvi, and S. Anjum, “RETRACTED: Fresnelet approach for image encryption in the algebraic frame,” Applied Mathematics and Computation, vol. 334, pp. 343-355, 2018, doi: 10.1016/j.amc.2018.03.105.
H. Yang, K.-W. Wong, X. Liao, W. Zhang, and P. Wei, “A fast image encryption and authentication scheme based on chaotic maps,” Communications in Nonlinear Science and Numerical Simulation, vol. 15, no. 11, pp. 3507-3517, 2010, doi: 10.1016/j.cnsns.2010.01.004.
X. Zhang, “Application of Knowledge Distillation in Generative Adversarial Networks,” 2023 3rd Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS), pp. 65-71, 2023, doi: 10.1109/acctcs58815.2023.00014.
A. A. Abd El-Latif and X. Niu, “A hybrid chaotic system and cyclic elliptic curve for image encryption,” AEU - International Journal of Electronics and Communications, vol. 67, no. 2, pp. 136-143, 2013, doi: 10.1016/j.aeue.2012.07.004.
T. Miyato and M. Koyama, “Generative Adversarial Network (GAN),” Computer Vision, pp. 508-513, 2021, doi: 10.1007/978-3-030-63416-2_860.
R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang, “The Unreasonable Effectiveness of Deep Features as a Perceptual Metric,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 586-595, 2018, doi: 10.1109/cvpr.2018.00068.
W. Sirichotedumrong, T. Maekawa, Y. Kinoshita, and H. Kiya, “Privacy-Preserving Deep Neural Networks with Pixel-Based Image Encryption Considering Data Augmentation in the Encrypted Domain,” 2019 IEEE International Conference on Image Processing (ICIP), pp. 674-678, 2019, doi: 10.1109/icip.2019.8804201.
M. Li, D. Lu, Y. Xiang, Y. Zhang, and H. Ren, “Cryptanalysis and improvement in a chaotic image cipher using two-round permutation and diffusion,” Nonlinear Dynamics, vol. 96, no. 1, pp. 31-47, 2019, doi: 10.1007/s11071-019-04771-7.
X. Chen, H. Ma, P. Ji, H. Liu, and Y. Liu, “Based on GAN Generating Chaotic Sequence,” Communications in Computer and Information Science, pp. 37-49, 2020, doi: 10.1007/978-981-33-4922-3_4.
M. Singh, N. Baranwal, K. N. Singh, and A. K. Singh, “Using GAN-Based Encryption to Secure Digital Images with Reconstruction through Customized Super Resolution Network,” IEEE Transactions on Consumer Electronics, vol. 70, no. 1, pp. 3977-3984, 2024, doi: 10.1109/tce.2023.3285626.
D. Zhao, “High-security and low-complexity OCDM transmission scheme based on GAN enhanced chaotic encryption,” Optics Express, vol. 30, no. 19, p. 34898, 2022, doi: 10.1364/oe.465522.
R. A. Hallman, “Poster EveGAN: Using Generative Deep Learning for Cryptanalysis,” Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, pp. 3355-3357, 2022, doi: 10.1145/3548606.3563493.
D. R. I. M. Setiadi, “PSNR vs SSIM: imperceptibility quality assessment for image steganography,” Multimedia Tools and Applications, vol. 80, no. 6, pp. 8423-8444, 2020, doi: 10.1007/s11042-020-10035-z.
U. Sara, M. Akter, and M. S. Uddin, “Image Quality Assessment through FSIM, SSIM, MSE and PSNR—A Comparative Study,” Journal of Computer and Communications, vol. 7, no. 3, pp. 8-18, 2019, doi: 10.4236/jcc.2019.73002.
A. Orman, “Image Retrieval Using Pixel Similarity,” Research Square, 2023, doi: 10.21203/rs.3.rs-3311259/v1.
P. Udayakumar and N. Rajagopalan, “(Retracted) Blockchain enabled secure image transmission and diagnosis scheme in medical cyber-physical systems,” Journal of Electronic Imaging, vol. 31, no. 6, 2022, doi: 10.1117/1.jei.31.6.062002.
R. Bhat and R. Nanjundegowda, "Comparative Analysis of CryptoGAN: Evaluating Quality Metrics and Security in GAN-based Image Encryption," Journal of Robotics and Control (JRC), vol. 5, no. 5, pp. 1557-1569, 2024.
V. Ilichev and I. Chukhraev, “Data processing using Deep Learning of the generative-adversarial neural network (GAN),” Neurocomputers, 2021, doi: 10.18127/j19998554-202105-04.
W. Serrano, “The Deep Learning Generative Adversarial Random Neural Network in data marketplaces: The digital creative,” Neural Networks, vol. 165, pp. 420-434, 2023, doi: 10.1016/j.neunet.2023.05.028.
Downloads
Published
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
This journal is based on the work at https://journal.umy.ac.id/index.php/jrc under license from Creative Commons Attribution-ShareAlike 4.0 International License. You are free to:
- Share – copy and redistribute the material in any medium or format.
- Adapt – remix, transform, and build upon the material for any purpose, even comercially.
The licensor cannot revoke these freedoms as long as you follow the license terms, which include the following:
- Attribution. You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- ShareAlike. If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
- No additional restrictions. You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
• Creative Commons Attribution-ShareAlike (CC BY-SA)
JRC is licensed under an International License
