A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
The DOI matches its Crossref record; 332 of the 332 references it cites were found in a registry or an index.
Abstract
Generative adversarial networks (GANs) have recently become a hot research topic; however, they have been studied since 2014, and a large number of algorithms have been proposed. Nevertheless, few comprehensive studies explain the connections among different GAN variants and how they have evolved. In this paper, we attempt to provide a review of the various GAN methods from the perspectives of algorithms, theory, and applications. First, the motivations, mathematical representations, and structures of most GAN algorithms are introduced in detail, and we compare their commonalities and differences. Second, theoretical issues related to GANs are investigated. Finally, typical applications of GANs in image processing and computer vision, natural language processing, music, speech and audio, the medical field, and data science are discussed.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Generative adversarial networks (GANs) [11] have gained interest as an important research topic in deep learning because they can generate synthetic samples that cannot be distinguished as true or false based on existing data.”
From Deep Learning-Based Optimization of Visual–Auditory Sensory Substitution (2023) · cites this paper as [11]
Citations
Cites
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 3×
“BigBiGAN achieve the state of the art in both unsupervised representation learning on ImageNet and unconditional image generation.”
BackgroundGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 2×
“MLP can be only used for small datasets such as CIFAR-10 [189], MNIST [190], and the Toronto Face Database (TFD) [191].”
MethodInfluentialRethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930 · cited 4×
“When paired training data is available, reference [156] can be used for these image-toimage translation tasks.”
BackgroundMethodInfluentialAuto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067 · cited 1×
“The explicit density models include maximum likelihood estimation (MLE), approximate inference [95], [96], and Markov chain method [97]–[99].”
MethodA fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · cited 1×
“The explicit density models include maximum likelihood estimation (MLE), approximate inference [95], [96], and Markov chain method [97]–[99].”
MethodMastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612 · cited 3×
“The intermediate version of AlphaGo utilizes two networks competing with each other.”
BackgroundPhoto-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.19 · Cited by 12,696
Research works printed but not linked: 17
- Schmidhuber, 1990, Making the world differentiable: On using fully recurrent self-supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments, Inst. Comput. Sci., Tech. Univ. Munich, Germany, FKI-126, Tech. Rep.
- Schmidhuber, 2009, Art & science as by-products of the search for novel patterns, or data compressible in unknown yet learnable ways, Edizioni, 98
- Goodfellow, Generative adversarial nets, 2672
- 10.1016/S0364-0213(85)80012-4 · doi:10.1016/s0364-0213(85)80012-4 · Paper page
- Gauthier, 2014, Conditional generative adversarial nets for convolutional face generation, Class Project for Stanford CS231N: Convolutional Neural Netw. Vis. Recognit., Winter semester, 2014
- Yao, 3D-aware scene manipulation via inverse graphics, 1887
- Gong, Twin auxilary classifiers GAN, 1328
- Uppal, Nonparametric density estimation & convergence of GANs under besov IPM losses, 9086
- Mroueh, Sobolev GAN
- Goodfellow, 2016, Deep Learning
- 10.1109/ICCV.2019.00460 · DOI · Paper page
- Singh, Nonparametric density estimation with adversarial losses, 10246
- Nagarajan, Theoretical insights into memorization in GANs, 1
- Cao, Learning a high fidelity pose invariant model for high-resolution face frontalization, 2867
- Zhang, Generating text via adversarial training, 1
- d’Autume, Training language GANs from scratch, 4302
- Rao, Answer-based adversarial training for generating clarification questions, 1
Cited by
Items 701–800 of 1,002
Deep Learning Models in Software Requirements EngineeringPreprint
Naumcheva, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.07771 · Cited by 6
“GANs and VAEs have been applied to such tasks as image generation [21], image-to-image translation [22], sound synthesis [23], data augmentation [24], music generation and natural language processing [25].”
MethodA Review on Remote Sensing Data Fusion with Generative Adversarial Networks (GAN)Preprint
Liu, P. (2021) · doi:10.36227/techrxiv.16607261.v1 · Cited by 6
Dey, S., Al-Ani, J. A., Bourazeri, A., Saha, S., Purkait, R., Hill, S., & Thompson, J. (2024) · Electronics · doi:10.3390/electronics13224541 · Cited by 5
“FID, widely used to evaluate the quality of generated images, particularly in Generative Adversarial Network(GAN)-based models [36–38], focuses on capturing the distributional difference between feature vectors of real and generated images.”
Highly Accurate Parallel AWG Interrogation System Using Neural Networks
Bing-xiang, L., Yuan, P., Lv, Z., Xu, Q. C., Miao, Q., Huang, J., & Zhu, L. (2025) · Journal of Lightwave Technology · doi:10.1109/jlt.2025.3526417 · Cited by 5
“Furthermore, to ensure compliance with cascading neural networks, the data is augmented with generative adversarial networks [17], [18] (GAN).”
An IPv6 target generation approach based on address space forest
Hao, S., Zhang, L., Zhang, H., Cheng, L., Guo, Y., Lin, B., Lin, B., Zhu, H., Ren, M., & Zhang, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-97640-w · Cited by 7
“The worst-case time complexity for constructing a 6ASTree is The space complexity for constructing a 6ASTree is O ( n log n ) .”
InfluentialElloumi, S., Bahroun, S., Yahia, S. B., & Kaddes, M. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9080191 · Cited by 6
Evaluation of StyleGAN-CLIP Models in Text-to-Image Generation of Faces
Fejjari, A., Abela, A., Tanti, M., & Muscat, A. (2025) · Applied Sciences · doi:10.3390/app15158692 · Cited by 6
AI-based hardware and software tools in microscopy to boost research in immunology and virology
Morone, D., & D’Antuono, R. (2025) · Frontiers in Immunology · doi:10.3389/fimmu.2025.1610345 · Cited by 5
“The generating network challenges the evaluating network, thus introducing an element of randomness and “ creativity ” in the output (458).”
Babu, A., Sadam, A., & Lermusiaux, P. F. J. (2026) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2025ms005324 · Cited by 9
“In contrast, GANs generate sharp samples by matching distributions (Gui et al., 2021), showing effectiveness for some inverse problems (Güemes et al., 2022; Patel et al., 2022).”
Ding, H., Wang, S., Yuan, X., Huang, N., & Cui, X. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104537 · Cited by 5
Mapping the technological evolution of generative AI: a patent network analysis
Mohammadi, N., Dahooie, J. H., Bengari, A. A., & Rahimi, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-26810-7 · Cited by 7
Generative Artificial Intelligence Models: A Survey
Almuammar, M., Alsultan, K., & Altukhaim, Y. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11546-1 · Cited by 9
“For example, some surveys provide an in-depth analysis of individual model families such as Transformers (Lin et al. 2022; Gardazi et al. 2025 ), GANs (Gui et al. 2021 ),VAEs (Li et al. 2023 ), or DMs (Yang et al. 2023; Chang et al. 2025 ).”
Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks
Krueger, P. P., Gottschalk, H., Werdelmann, B., & Krebs, W. (2024) · Journal of Engineering for Gas Turbines and Power · doi:10.1115/1.4066294 · Cited by 6
“However, they are prone to mode collapse and poor coverage of all alternatives compatible with a given prompt [13].”
Ding, H., Huang, N., Wu, Y., & Cui, X. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3480890 · Cited by 5
“1) GAN: GAN is a generative model based on game theory, typically consisting of two independent networks: a generator ( G ) and a discriminator ( D ) [26].”
Toward AI/ML-assisted discovery of transition metal complexes
Jin, H., & Merz, K. M. (2024) · Annual reports in computational chemistry · doi:10.1016/bs.arcc.2024.10.003 · Cited by 5
Azadmanesh, M., Ghahfarokhi, B. S., & Talouki, M. A. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125646 · Cited by 6
Simulating Accelerometer Signals of Parkinson’s Gait Using Generative Adversarial Networks
Hadley, A. J., & Pulliam, C. L. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10781879 · Cited by 5
“More recently, generative adversarial networks (GANs) have brought about a significant advancement in the field of data augmentation [11].”
Dehazing using Generative Adversarial Network - A Review
Khatun, A., Mostafiz, R., Shorif, S. B., Uddin, M. S., & Hadi, M. A. (2024) · SN Computer Science · doi:10.1007/s42979-024-03571-0 · Cited by 5
“In recent years, significant advancements in hardware have contributed to the notable progress of GAN [47–51].”
Sketches to Realistic Images: A Multi-GAN based Image Generation System
Uke, S. N., Surase, O., Solunke, T., Marne, S., & Phadke, S. (2024) · International Conference on Data Intelligence and Cognitive Informatics (ICDICI) · doi:10.1109/icdici62993.2024.10810943 · Cited by 6
“J Gui et al. [11] explored recent findings and applications of GANs related to computer vision, comparing various GAN architectures and approaches.”
Conditional diffusion-generated super-resolution for myocardial perfusion MRI
Sun, C., Goyal, N., Wang, Y., Tharp, D. L., Kumar, S., & Altes, T. A. (2025) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2025.1499593 · Cited by 9
Animal-skin-pattern-inspired multifunctional composites by generative AI
Masrouri, M., Jadhav, A. V., & Zhao Qin, A. (2025) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2025.102428 · Cited by 5
Amo-Boateng, M., & Adu-Gyamfi, Y. O. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106122 · Cited by 5
Yin, Y., Huang, D., Qin, N., Li, K., Wang, T., & Zong, R. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3565027 · Cited by 5
“GANs exhibit superior conditional control and diversity in generated data [30], while VAEs are less prone to mode collapse and easier to train, though they generally produce lower quality data compared to GANs [31].”
Robust Multiple-Fault Diagnosis of PMSMs in Dynamic Operations Under Imbalanced Datasets
Nguyen, D., Khang, H. V., & Robbersmyr, K. G. (2025) · IEEE Transactions on Transportation Electrification · doi:10.1109/tte.2025.3566612 · Cited by 6
“However, training these networks requires large-scale, accurately labeled data, which is not available for PMSM drives in dynamic operations [7], [14].”
Jiang, T., Dong, Q., Ma, Y., Ji, X., & Liu, Y. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128222 · Cited by 9
VL-GAN: A generative classification approach for fingerprint-based indoor localization
Mallik, M., Chakraborty, S., Sasidhar, K., & Chowdhury, C. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128400 · Cited by 6
Zhou, C., He, J., Yang, S., Xiong, X., & Chi, Y. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103646 · Cited by 5
Balancing Act: MDGAN for Imbalanced Tabular Data Synthesis
Ding, H., Huang, N., Tao, Q., Liang, J., & Cui, X. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3607862 · Cited by 5
“Researchers have proposed variants such as Least Squares GAN (LSGAN), Wasserstein GAN (WGAN), Wasserstein GAN with Gradient Penalty (WGAN-GP), and Spectral Normalization GAN (SNGAN) to improve the quality and diversity of synthetic samples [6].”
Shi, M., Yang, H., Niu, Z., Zeng, C., Zhang, Y., Xiao, J., Chen, M., Hu, W., & Yi, L. (2026) · Journal of Lightwave Technology · doi:10.1109/jlt.2026.3659990 · Cited by 5
“However, the adversarial training process in CGAN is prone to instability and may fail to converge to optimal performance [70], [71], which particularly limits its applicability in multi-channel WDM systems.”
A Review of Recent Trends and Industry Prospects for Artificial Intelligence Technologies
Li, G., Wang, X., & Li, M. (2021) · International Conference on Behavioral, Economic, and Socio-Cultural Computing · doi:10.1109/besc53957.2021.9635368 · Cited by 7
Generation of Synthetic Rat Brain MRI Scans with a 3D Enhanced Alpha Generative Adversarial Network
Ferreira, A. F., Magalhães, R. J. D. S., Mériaux, S., & Alves, V. (2022) · Applied Sciences · doi:10.3390/app12104844 · Cited by 12
“5 is the optimal solution, as this means that the discriminator is not able to distinguish the real images from the fake ones [19,20].”
BackgroundArabic Emotional Voice Conversion Using English Pre-Trained StarGANv2-VC-Based Model
Meftah, A. H., Alotaibi, Y. A., & Selouani, S. (2022) · Applied Sciences · doi:10.3390/app122312159 · Cited by 5
“Recently, generative adversarial networks (GANs), with their different variants (e.g., cycle-consistent generative adversarial network (CycleGAN, StarGANs, etc.), and autoencoder are the most common techniques used in EVC frameworks [1,10].”
MethodRevolutionizing Program Evaluation with Generative AI: An Evidence-Based Methodology
-, D. P. (2023) · International Journal For Multidisciplinary Research · doi:10.36948/ijfmr.2023.v05i03.4105 · Cited by 9
“GANs can provide a number of advantages over other generative algorithms, such as better performance, quicker training, and more accurate results [14].”
BackgroundMembership inference attack on differentially private block coordinate descent
Riaz, S., Ali, S., Wang, G., Latif, M. A., & Iqbal, M. Z. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1616 · Cited by 6
Bhattacharya, S., Bhattacharya, A., & Shahnawaz, S. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00418 · Cited by 8
“Generative Adversarial Networks (GANs) have been proven to be very effective in generating synthetic data [16].”
BackgroundHigh-Fidelity Synthetic Face Generation for Rosacea Skin Condition from Limited Data
Mohanty, A., Sutherland, A., Bezbradica, M., & Javidnia, H. (2024) · Electronics · doi:10.3390/electronics13020395 · Cited by 11
What Is Generative in Generative Artificial Intelligence? A Design-Based Perspective
Bordas, A., Masson, P. L., Thomas, M., & Weil, B. (2024) · Springer eBooks · doi:10.1007/978-3-031-71922-6_8 · Cited by 7
Iterative Optimization-Enhanced Contrastive Learning for Multimodal Change Detection
Tang, Y., Yang, X., Han, T., Sun, K., Guo, Y., & Hu, J. (2024) · Remote Sensing · doi:10.3390/rs16193624 · Cited by 5
Generating online freight delivery demand during COVID-19 using limited data
Mirzanezhad, M., Twumasi-Boakye, R., Fabusuyi, T., & Broaddus, A. (2024) · Transportation Research Part B Methodological · doi:10.1016/j.trb.2024.103100 · Cited by 6
Traquete, F., Silva, M. S., & Ferreira, A. E. N. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109414 · Cited by 5
Cardiac disease diagnosis based on GAN in case of missing data
Chen, X., Zhang, N., Yang, X., Wang, C., Qi, N., Luan, T., Zhu, W., Zhang, C., & Yang, C. (2024) · PLoS ONE · doi:10.1371/journal.pone.0292480 · Cited by 5
Multi-level social network alignment via adversarial learning and graphlet modeling
Duan, J., Zhao, K., Tian, L., & Xin, Y. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107230 · Cited by 5
The generative adversarial network improved by channel relationship learning mechanisms
Yue, D., Luo, J., & Li, H. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.04.123 · Cited by 5
Combining machine learning with physics: A framework for tracking and sorting multiple dark solitons
Guo, S., Koh, S. M., Fritsch, A. R., Spielman, I. B., & Zwolak, J. P. (2022) · Physical Review Research · doi:10.1103/physrevresearch.4.023163 · Cited by 7
“From the ML perspective, adding modules based on unsupervised [46], active learning [47], and synthetic data generation with generative models [48] may further enhance the performance of the SolDet framework.”
MethodConvolution-LSTM-Based Mechanical Hard Disk Failure Prediction by Sensoring S.M.A.R.T. Indicators
Shi, J., Du, J., Ren, Y., Li, B., Zou, J., & Zhang, A. (2022) · Journal of Sensors · doi:10.1155/2022/7832117 · Cited by 5
“V G,D ð Þ = Ex~Pdata logD x ð Þ 1⁄2 + Ex~PG log 1 −D x ð Þ ð Þ 1⁄2 : ð8Þ The objective function is as follows [36]:”
BackgroundRetractedBPDGAN: A GAN-Based Unsupervised Back Project Dense Network for Multi-Modal Medical Image Fusion
Liu, S., & Yang, L. (2022) · Entropy · doi:10.3390/e24121823 · Cited by 5
“Therefore, a generative adversarial network (GAN) [26] is employed in this paper.”
MethodLim, H., Chon, K.-W., & Kim, M. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120193 · Cited by 5
MTM: a multi-task learning framework to predict individualized tissue gene expression profiles
He, G., Chen, M., Bian, Y., & Yang, E. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad363 · Cited by 6
Anomaly Detection - Recent Advances, AI and ML Perspectives and Applications
Krishna Parimala, V. (2023) · Artificial intelligence · doi:10.5772/intechopen.110988 · Cited by 6
Chaghazardi, Z., Fallah, S., & Tamaddoni‐Nezhad, A. (2023) · Electronic Proceedings in Theoretical Computer Science · doi:10.4204/eptcs.385.21 · Cited by 8
Vora, N., Polleys, C. M., Sakellariou, F., Georgalis, G., Thieu, H.-T. N., Genega, E. M., Jahanseir, N., Patra, A., Miller, E. L., & Georgakoudi, I. (2023) · Journal of Biomedical Optics · doi:10.1117/1.jbo.28.12.126006 · Cited by 6
Generative approaches for solving tangram puzzles
Yamada, F. M., Batagelo, H. C., Gois, J. P., & Takahashi, H. (2024) · Discover Artificial Intelligence · doi:10.1007/s44163-024-00107-6 · Cited by 6
“These are typically implemented using neural networks but could be implemented using any form of differentiable system that maps data from one space to another [60].”
A Data Augmentation Method for Side-Channel Attacks on Cryptographic Integrated Circuits
Cui, X., Zhang, H., Xu, J., Fang, X., Ning, W., Wang, Y., & Hosen, M. S. (2024) · Electronics · doi:10.3390/electronics13071348 · Cited by 7
Virtual sensor for probabilistic estimation of the evaporation in cooling towers
Alonso, S., Morán, A., Pérez, D., Prada, M. A., Fuertes, J. J., & Domínguez, M. (2021) · Integrated Computer-Aided Engineering · doi:10.3233/ica-210654 · Cited by 5
Liang, Z., & Zhang, S. (2021) · IEEE Access · doi:10.1109/access.2021.3103669 · Cited by 5
“Nevertheless, the techniques of GAN have been applied in some NLP areas [16], including melody generation from lyrics [17], machine translation [18], relation extraction [19], finding knowledge items in knowledge graphs [20], and dialogue generation [21].”
BackgroundMethodGenerative Adversarial Networks: Solution for Handling Imbalanced Datasets in Computer Vision
Pattanayak, D., & Patel, K. (2022) · International Conference for Advancement in Technology (ICONAT) · doi:10.1109/iconat53423.2022.9725995 · Cited by 5
Arun, P. V., & Karnieli, A. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07019-5 · Cited by 5
“The selected benchmark approaches are improved versions of the ones that reported the state-of-the-art results [1, 2, 4, 12, 17, 28, 33, 34, 42, 48, 65, 83, 85].”
BackgroundDebelie, A., Bagui, S. S., Mink, D., & Bagui, S. (2026) · Technologies · doi:10.3390/technologies14020117 · Cited by 5
“The goal of the GAN training process is to maximize E x ∼ p data ( x ) [ logD ( x )] to increase the accuracy of discerning real data while G minimizes log ( 1 − D ( G ( z ))) to increase the probability of fooling the discriminator [9,10].”
InfluentialKöse, U., Deperlioğlu, Ö., Küçüksille, E. U., & TURAN, G. (2024) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict60155.2024.10544998 · Cited by 4
“The final step of the methodology builds the shole decision support system, by using the GAN technique, which is able to generate very realistic synthetic data by considering the original data [65].”
MethodIntuitively interpreting GANs latent space using semantic distribution
Wang, R., Wang, G., Gu, L., Liu, Q., Liu, Y., & Guo, Y. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112894 · Cited by 5
Yu, B., Yan, J., Li, Y.-A., & Xing, H. (2025) · Georisk Assessment and Management of Risk for Engineered Systems and Geohazards · doi:10.1080/17499518.2025.2453930 · Cited by 6
“Each iteration of training moves the generator closer to producing data that the discriminator can no longer reliably classify as fake, thereby enhancing the overall model’s capability to mimic the real data distribution (Gui et al. 2021).”
Hussien, G. H., & Nemer, Z. N. (2025) · Iraqi Journal of Intelligent Computing and Informatics (IJICI) · doi:10.52940/ijici.v4i1.90 · Cited by 4
“[31].”
Swadi, L. A., & Al-Mashhadi, H. M. (2025) · Iraqi Journal of Intelligent Computing and Informatics (IJICI) · doi:10.52940/ijici.v4i1.65 · Cited by 4
Improved generative adversarial networks model for movie dance generation
Lin, Z., & Feng, K. (2025) · PLoS ONE · doi:10.1371/journal.pone.0323304 · Cited by 4
A Critical Review on Machine Vision in Potato Production: From Cultivation to Storage
Li, X., Xing, W., Ma, J., He, W., Cao, Y., Li, A., Xu, Y., & Ming, W. (2025) · Journal of Food Process Engineering · doi:10.1111/jfpe.70142 · Cited by 4
Zeng, S., Lan, S., Xu, Z., Hu, S., Li, M., Liu, S., & Chen, T. (2025) · Design and Artificial Intelligence · doi:10.1016/j.daai.2025.100020 · Cited by 4
Liu, J., & Wu, Y. (2025) · Electrical Engineering · doi:10.1007/s00202-025-03301-6 · Cited by 4
Reduced storage direct tensor ring decomposition for convolutional neural networks compression
Gabor, M., & Zdunek, R. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107994 · Cited by 8
Dong, X., Zhang, H., Xu, Z., Han, H., Jiang, L., & Liu, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130159 · Cited by 6
Conditional GAN Approaches on Regression Labels: A State‐of‐the‐Art Review
Silva‐Silverio, A., Gómez-Gil, P., & Sánchez-Argüelles, D. (2025) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.70050 · Cited by 5
FairGFL: Privacy-Preserving Fairness-Aware Federated Learning With Overlapping Subgraphs
Zhou, Z., Yang, S., Zhao, F., & Ren, X. (2026) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2025.3649863 · Cited by 4
“However, the honest but curious server could potentially leverage a well-designed decoder to recover private information [50], [51].”
Quantum generative modeling for financial time series with temporal correlations
Dechant, D., Schwander, E., Drooge, L. V., Moussa, C., Garlaschelli, D., Dunjko, V., & Tura, J. (2026) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ae39a2 · Cited by 10
“Typically, GANs are applied in image generation [4–6], but also to other data [7].”
Deep learning approaches in computer vision: a comprehensive survey
Reshadi, S., TaghipourEivazi, S., Ghaffari, A., & Seyyedabbasi, A. (2026) · Cluster Computing · doi:10.1007/s10586-026-06045-5 · Cited by 4
“However, there can be a trade-off in model accuracy when trying to balance fairness with performance [74–76].”
Naresh, C., & Mathew, A. (2026) · Environmental Modeling & Assessment · doi:10.1007/s10666-026-10131-8 · Cited by 4
“GAN-generated data can also be integrated with drought indicators to quantify severity, frequency, and spatial extent, enabling improved historical and future drought analyses [100].”
Mathematical analysis of loss function of GAN and its loss function variants
(2022) · International Journal of Advanced Technology and Engineering Exploration · doi:10.19101/ijatee.2021.875738 · Cited by 5
Generative Adversarial Networks as an Accommodative Memory for Cognitive Waveform Synthesis
Najafabadi, H. E., Leung, H., & Moo, P. W. (2023) · IEEE Transactions on Radar Systems · doi:10.1109/trs.2023.3286283 · Cited by 4
“In particular, Wasserstein GAN (WGAN) [33] is deemed as the most promising [1].”
BackgroundOn the Application of Artificial Intelligence in Local Legislation
Wang, K. (2023) · Applied Mathematics and Nonlinear Sciences · doi:10.2478/amns.2023.1.00371 · Cited by 6
Damage GAN: A Generative Model for Imbalanced Data
Anaissi, A., Jia, Y., Braytee, A., Naji, M., & Alyassine, W. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-8696-5_4 · Cited by 7
“The main idea of the generative model is to learn the pattern of the training data and use that knowledge to create new examples[11,30,29].”
BackgroundPacheco, F., Cerrada, M., & Huertas, J. I. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107665 · Cited by 4
A Synergistic MOEA Algorithm with GANs for Complex Data Analysis
Qian, W., Xu, H., Chen, H., Yang, L., Lin, Y., Xu, R., Yang, M., & Liao, M. (2024) · Mathematics · doi:10.3390/math12020175 · Cited by 4
Few-shot learning and modeling of 3D reservoir properties for predicting oil reservoir production
Cirac, G., Avansi, G. D., Farfan, J., Schiozer, D. J., & Rocha, A. D. R. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09834-4 · Cited by 4
“DC-GANs are a class of generative algorithms inspired by game theory, where the two agents involved learn cyclically in a competition [27].”
Realistic real-time processing of anime portraits based on generative adversarial networks
Zhu, G., Qu, Z., Sun, L., Liu, Y., & Yang, J. (2024) · Journal of Real-Time Image Processing · doi:10.1007/s11554-024-01481-1 · Cited by 9
“A convolutional kernel of the size 3 was used, the Adam optimizer [32] was used in the network, and the ReLU function [33] and Tanh function were used for the activation function [34].”
Lee, J.-K., Chae, S., Yang, E., & Hong, S. W. (2024) · Journal of Asian Architecture and Building Engineering · doi:10.1080/13467581.2024.2389163 · Cited by 4
“Generative models span a wide spectrum and extend to areas such as medicine and data science, where they are integral to tasks such as object detection and video manipulation (Gui et al. 2021).”
Comparing Boosting-Based and GAN-Based Models for Intrusion Detection in 5G Networks
Moubayed, A. (2024) · International Symposium on Networks, Computers and Communications (ISNCC) · doi:10.1109/isncc62547.2024.10759066 · Cited by 5
“Those sub-models are typically implemented using neural networks, but are adaptable to any differentiable system [15].”
InfluentialLightweight GAN-Assisted Class Imbalance Mitigation for Apple Flower Bud Detection
Yuan, W., & Li, P. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9020028 · Cited by 5
TANGAN: solving Tangram puzzles using generative adversarial network
Yamada, F. M., Batagelo, H. C., Gois, J. P., & Takahashi, H. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06364-x · Cited by 7
“The generator tries to capture the distribution of true examples and generate new data examples, while the discriminator is usually a binary classifier used to discriminate generated examples from real examples as accurately as possible [23].”
Tanawala, B., & Dalwadi, D. C. (2025) · SN Computer Science · doi:10.1007/s42979-025-03855-z · Cited by 4
Cyber Security for Hoax News Detection with Similarity Algorithm
Yakub, S. Y., Agustriawan, D., Irmawati, I., Kristiyanti, D. A., Sahib, S., Abdollah, M. F., Al‐Mhiqani, M. N., & Durachman, Y. (2024) · International Conference on Informatics and Computing (ICIC) · doi:10.1109/icic64337.2024.10956546 · Cited by 6
“With this development, as technology becomes more sophisticated, AI can process images [11] to produce realistic imitations, or fake images, that are quite convincing.”
Li, C., Liu, W., Ma, W., & Yang, H. (2025) · Transportation Science · doi:10.1287/trsc.2023.0326 · Cited by 4
MD-GAN: Multi-Scale Diversity GAN for Large Masks Inpainting
Wang, S., Guo, X., & Guo, W. (2025) · Electronics · doi:10.3390/electronics14112218 · Cited by 4
Pulford, G. W., & Kondrashov, K. (2021) · IEEE Access · doi:10.1109/access.2021.3133762 · Cited by 4
“Among the better known ones are: convergence failure, where the SGD algorithm stalls due to near zero gradient [7], and mode collapse [8]–[10] where only a subset of a multi-modal data distribution is captured during generator training [11], including the case of collapse to a single point [2].”
BackgroundReconstructing Medical Images Using Generative Adversarial Networks: A Study
Buch, P., & Thakkar, A. R. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-5037-7_6 · Cited by 4
A Novel Hybrid DL Model for Printed Arabic Word Recognition based on GAN
Alwaqfi, Y. M., Mohamad, M., Al‐Taani, A. T., & Hamid, N. A. (2023) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2023.0140165 · Cited by 4
“Through adversarial learning, the generator and discriminator both get better [27], [28].”
BackgroundDigital solutions for bespoke apparel achieving mass customization in as service business models
DIMCEA, I., Cozmiuc, D., Botez, D., Darvasi, D., Untaru, M., Wagner, R., & Ţîțu, A. M. (2023) · Industria Textila · doi:10.35530/it.074.01.202281 · Cited by 4
Ma, Z., Chen, Y., Fan, Y., He, X., Luo, W. Z., & Shu, J. (2023) · Applied Sciences · doi:10.3390/app13158699 · Cited by 4
Idecomp: imbalance-aware decomposition for class-decomposed classification using conditional GANs
Buczek, P., Zidan, U., Gaber, M. M., & Abdelsamea, M. M. (2023) · Discover Artificial Intelligence · doi:10.1007/s44163-023-00078-0 · Cited by 4
“Furthermore [16], discuss how GANs have been used to generate and design DNA, drug discovery, generate multilabel discrete patient records, medical image processing, and doctor recommendation.”
Avram, A.-M., Mititelu, V. B., & Cercel, D.-C. (2023) · Workshop on Multiword Expressions (MWE) · doi:10.18653/v1/2023.mwe-1.4 · Cited by 10
Game-Theoretic Flexible Resource Allocation for Handoff in Hybrid V2X Communication
Sharma, S., Ghosh, S., Bhatnagar, M. R., & Panigrahi, B. K. (2023) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc56721.2023.10293867 · Cited by 4
“It is influenced by the iterative gradient descent methods in [20]-[21] in which each player takes a significant step towards lowering their objective while the strategies of the other players remain fixed.”
BackgroundMultimodal Person Verification With Generative Thermal Data Augmentation
Abdrakhmanova, M., Unaspekov, T., & Varol, H. A. (2023) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2023.3346938 · Cited by 5
“Further developements on GANs have extended this framework to various computer vision tasks, such as picture production and domain transfer, with impressive results [23].”
BackgroundIonescu, B. E., Müller, H., Drăgulinescu, A., Idrissi-Yaghir, A., Radzhabov, A., de Herrera, A. G. S., Andrei, A.-G., Stan, A., Storås, A. M., Abacha, A. B., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56072-9_6 · Cited by 4
“…tasks approaching different aspects of mono-and cross-language information retrieval systems [14,18,19] related to the interpretation of the radiology images [25], and testing the hypothesis that the artificial biomedical images contain fingerprints of the original images [6,12], to name a few.”
Background
Metadata
- Authors
- Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J.
- Affiliations
- University of Michigan (US)
- Chinese Academy of Sciences (CN)
- Nanyang Technological University (SG)
- The University of Sydney (AU)
- Venue
- IEEE Transactions on Knowledge and Data Engineering
- Published
- 2023-04-01
- Volume
- 35
- Issue
- 4
- Pages
- 3313-3332
- ISSN
- 1041-4347 (ISSN-L)
- 1558-2191
- 2326-3865
- OpenAlex
- W3216759837
- Cited by
- 1,231
- References
- 329
- Citations by year
- 2026: 181 · 2025: 304 · 2024: 341 · 2023: 216
- FWCI
- 65.28
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Knowledge and Data Engineering (publishedVersion)
- DR-NTU (Nanyang Technological University) (submittedVersion)
- Funders
- National Natural Science Foundation of China (62172090, 62172089)
- National Key R&D Project of China (2021QY2102)
- CAAI-Huawei MindSpore Open Fund
- Alibaba Innovative Research Program
- Fundamental Research Funds for the Central Universities (2242022R10071)
- National Research Foundation Singapore
- Jiangsu Provincial Double-Innovation Doctor Program (JSSCBS20210075)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- generative adversarial networks, GAN variants, generative models, image generation, image processing, natural language generation, music generation, medical image synthesis, data science applications
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.