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 101–200 of 1,002
Nassra, I., & Capella, J. V. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100806 · Cited by 101
Generative AI in mobile networks: a survey
Karapantelakis, A., Alizadeh, P., Alabbasi, A., Dey, K., & Nikou, A. (2023) · Annals of Telecommunications · doi:10.1007/s12243-023-00980-9 · Cited by 116
The Role of Generative Adversarial Network in Medical Image Analysis: An In-depth Survey
Alamir, M., & Alghamdi, M. (2022) · ACM Computing Surveys · doi:10.1145/3527849 · Cited by 102
“Accordingly, G learns to create a sample from just a few modes of the data distribution and ignore the other modes even if it is trained on them [60].”
BackgroundInfluentialA review on infrared and visible image fusion algorithms based on neural networks
Yang, K., Xiang, W., Chen, Z., Zhang, J., & Liu, Y. (2024) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2024.104179 · Cited by 100
A semi-supervised GAN method for RUL prediction using failure and suspension histories
He, R., Tian, Z., & Zuo, M. J. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2021.108657 · Cited by 91
A Comprehensive Survey of Machine Learning Methods for Surveillance Videos Anomaly Detection
Choudhry, N., Abawajy, J., Huda, S., & Rao, I. (2023) · IEEE Access · doi:10.1109/access.2023.3321800 · Cited by 87
“Gui and Sun [70] attempt to offer a comprehensive review of various GANs, focusing on algorithms, theory, and software packages.”
BackgroundLiu, P., Li, J., Wang, L., & He, G. (2022) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2022.3165967 · Cited by 95
The knowledge and innovation challenges of ChatGPT: A scoping review
Ali, O., Murray, P., Momin, M., & Al–Anzi, F. S. (2023) · Technology in Society · doi:10.1016/j.techsoc.2023.102402 · Cited by 90
Deep image captioning: A review of methods, trends and future challenges
Xu, L., Tang, Q., Lv, J., Zheng, B., Zeng, X., & Li, W. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126287 · Cited by 95
Illumination Unification for Person Re-Identification
Zhang, G., Luo, Z., Chen, Y., Zheng, Y., & Lin, W. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3169422 · Cited by 86
TransCFD: A transformer-based decoder for flow field prediction
Jiang, J., Li, G., Jiang, Y., Zhang, L., & Deng, X. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106340 · Cited by 83
Gupta, P., Mahajan, R., Badhera, U., & Kushwaha, P. S. (2024) · The International Journal of Management Education · doi:10.1016/j.ijme.2024.101017 · Cited by 101
Multi-Grained Attention Networks for Single Image Super-Resolution
Wu, H., Zou, Z., Gui, J., Zeng, W., Ye, J., Zhang, J., Liu, H., & Wei, Z. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2988895 · Cited by 81
“They employed a simplified ResNet [22]–[24] architecture by removing the normalization layers in the SRResNet [15] and won the championship of the NTIRE2017 super-resolution challenge [25].”
MethodSelf-citationGao, S., Zhao, W., Wan, C., Jiang, H., Ding, Y., & Xue, S. (2022) · Measurement · doi:10.1016/j.measurement.2022.112095 · Cited by 84
Machine-Learning-Driven Advanced Characterization of Battery Electrodes
Finegan, D. P., Squires, I., Dahari, A., Kench, S., Jungjohann, K., & Cooper, S. J. (2022) · ACS Energy Letters · doi:10.1021/acsenergylett.2c01996 · Cited by 76
Applications of deep learning in electron microscopy
Treder, K. P., Huang, C., Kim, J. S., & Kirkland, A. I. (2021) · Microscopy · doi:10.1093/jmicro/dfab043 · Cited by 89
“(3), this can be expressed as an image restoring function: In contrast to a conventional CNN, a GAN architecture sets a generative model G against a discriminative model D where both are typically neural networks on their own [19].”
What Is the Role of AI for Digital Twins?
Emmert‐Streib, F. (2023) · AI · doi:10.3390/ai4030038 · Cited by 95
Machine learning applications in forensic DNA profiling: A critical review
Barash, M., McNevin, D. B., Fedorenko, V. A., & Giverts, P. (2023) · Forensic Science International Genetics · doi:10.1016/j.fsigen.2023.102994 · Cited by 92
Niu, Y., Wang, Y. D., Mostaghimi, P., Świętojański, P., & Armstrong, R. T. (2020) · Geophysical Research Letters · doi:10.1029/2020gl089029 · Cited by 77
Wavelet-packets for deepfake image analysis and detection
Wolter, M., Blanke, F., Heese, R., & Garcke, J. (2022) · Machine Learning · doi:10.1007/s10994-022-06225-5 · Cited by 69
GAN Slimming: All-in-One GAN Compression by a Unified Optimization Framework
Wang, H., Gui, S., Yang, H., Liu, J., & Wang, Z. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58548-8_4 · Cited by 90
DP-TrajGAN: A privacy-aware trajectory generation model with differential privacy
Zhang, J., Huang, Q., Huang, Y., Ding, Q., & Tsai, P. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.12.027 · Cited by 94
What is generative in generative artificial intelligence? A design-based perspective
Bordas, A., Masson, P. L., Thomas, M., & Weil, B. (2024) · Research in Engineering Design · doi:10.1007/s00163-024-00441-x · Cited by 105
Machine Learning for Industry 4.0: A Systematic Review Using Deep Learning-Based Topic Modelling
Mazzei, D., & Ramjattan, R. (2022) · Sensors · doi:10.3390/s22228641 · Cited by 99
“Direct applications aside from training data synthesis also include, among others, image processing such as restoration or superresolution, image-to-image translation, generating music and drug discovery [58,59].”
BackgroundRajabi, M. M., Komeilian, P., Wan, X., & Farmani, R. (2023) · Water Research · doi:10.1016/j.watres.2023.120012 · Cited by 74
Recent Advances in Generative Adversarial Networks for Gene Expression Data: A Comprehensive Review
Lee, M. (2023) · Mathematics · doi:10.3390/math11143055 · Cited by 83
Artificial Intelligence in Optical Communications: From Machine Learning to Deep Learning
Wang, D., & Zhang, M. (2021) · Frontiers in Communications and Networks · doi:10.3389/frcmn.2021.656786 · Cited by 75
“Inspired by GAN, a number of new applications have been discovered in terms of images, such as image synthesis, image style transfer, image-to-image translation, and image reconstruction (Gui J. et al., 2020).”
MethodExplainable reinforcement learning for broad-XAI: a conceptual framework and survey
Dazeley, R., Vamplew, P. W., & Cruz, F. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08423-1 · Cited by 107
“For instance one approach used for this is the utilisation of generative adversarial networks (GANs) [5, 93, 85] and even recurrent generative adversarial networks (RGANs) [151, 193].”
BackgroundEleven quick tips for data cleaning and feature engineering
Chicco, D., Oneto, L., & Tavazzi, E. (2022) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1010718 · Cited by 94
AutoGAN-Distiller: Searching to Compress Generative Adversarial NetworksPreprint
Fu, Y., Chen, W., Wang, H., Li, H., Lin, Y., & Wang, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.08198 · Cited by 89
Hertlein, N., Buskohl, P. R., Gillman, A. S., Vemaganti, K. S., & Anand, S. (2021) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2021.04.007 · Cited by 67
Al-Qaysi, N., Al‐Emran, M., Al-Sharafi, M. A., Iranmanesh, M., Ahmad, A., & Mahmoud, M. A. (2024) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2024.2361210 · Cited by 77
“The roots of GAI can be traced back to the 1960s, although it was not until around 2014 that the research community seriously focused on studying GAI (Gui et al., 2023).”
Using Wasserstein Generative Adversarial Networks for the design of Monte Carlo simulations
Athey, S. C., Imbens, G. W., Metzger, J., & Munro, E. (2021) · Journal of Econometrics · doi:10.1016/j.jeconom.2020.09.013 · Cited by 132
Creativity and Machine Learning: A Survey
Franceschelli, G., & Musolesi, M. (2024) · ACM Computing Surveys · doi:10.1145/3664595 · Cited by 101
“For an in-depth survey about the GANs, we refer to [39].”
BackgroundA review on Single Image Super Resolution techniques using generative adversarial network
Singla, K., Pandey, R., & Ghanekar, U. (2022) · Optik · doi:10.1016/j.ijleo.2022.169607 · Cited by 69
Games of GANs: game-theoretical models for generative adversarial networks
Moghaddam, M. M., Boroomand, B., Jalali, M. H., Zareian, A., Daeijavad, A., Manshaei, M. H., & Krunz, M. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10395-6 · Cited by 82
“The literatures in the first category (Goodfellow 2016; Wang et al. 2017; Creswell et al. 2018; Hitawala 2018; Gonog and Zhou 2019; Hong et al. 2019; Bissoto et al. 2019; Zhang et al. 2018a; Pan et al. 2019; Kumar and Jayagopal 2021; Salehi et al. 2020; Ghosh et al. 2020; Saxena and Cao 2020; Gui et al. 2020; Jabbar e…”
BackgroundEvaluating generative AI integration in Saudi Arabian education: a mixed-methods study
Alammari, A. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.1879 · Cited by 38
Lee, L., Wei, X., Chui, K. T., Cheung, S. K. S., Wang, F. L., Fung, Y.-C., Lu, A., Hui, Y. K., Hao, T., Leong Hou, U., et al. (2024) · Electronics · doi:10.3390/electronics13050890 · Cited by 85
Generative adversarial networks for prognostic and health management of industrial systems: A review
Li, Q. '., Tang, Y., & Chu, L. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124341 · Cited by 70
Amimeur, T., Shaver, J. M., Ketchem, R. R., Taylor, J. A., Clark, R. H., Smith, J., Van Citters, D., Siska, C. C., Smidt, P., Sprague, M., et al. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.04.12.024844 · Cited by 63
Liu, C., Chen, K., Zhao, R., Zou, Z., & Shi, Z. (2025) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2025.3560455 · Cited by 122
“Despite these successes, GAN-based models are often hindered by challenges, such as mode collapse and training instability, which can limit their effectiveness in generating diverse and high-quality images [44], [45].”
Generating Mobility Trajectories with Retained Data Utility
Cao, C., & Li, M. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467158 · Cited by 89
“[1, 14] show more GAN applications, which are proved to perform well in image-related tasks.”
BackgroundGenerative Adversarial Networks: A Survey on Attack and Defense Perspective
Zhang, C., Yu, S., Tian, Z., & Yu, J. J. Q. (2023) · ACM Computing Surveys · doi:10.1145/3615336 · Cited by 83
“[47] 2021 − ✓ ✓ ✓ Theoretical analysis on mode collapse.”
GAN-based generation of realistic 3D volumetric data: A systematic review and taxonomy
Ferreira, A. F., Li, J., Pomykala, K. L., Kleesiek, J., Alves, V., & Egger, J. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103100 · Cited by 88
Henkes, A., & Wessels, H. (2022) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2022.115497 · Cited by 71
Generative Adversarial Networks for Image Super-Resolution: A Survey
Wu, Z., Zhang, X., Yu, Y., Zhu, Q., Lin, J. C.-W., & Tian, C. (2026) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2026.078842 · Cited by 78
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?Preprint
Sehwag, V., Mahloujifar, S., Handina, T., Dai, S., Xiang, C., Chiang, M., & Mittal, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.09425 · Cited by 134
“In particular, generative adversarial networks (GANs) have excelled at this task (Goodfellow et al., 2014; Karras et al., 2020; Gui et al., 2020).”
BackgroundZielinski, C., Winker, M. A., Aggarwal, R., Ferris, L. E., Heinemann, M., Lapeña, J. F., Pai, S. A., Ing, E., Citrome, L., Alam, M., et al. (2024) · Current Medical Research and Opinion · doi:10.1080/03007995.2023.2286102 · Cited by 59
“Winker (2), Rakesh Aggarwal (3), Lorraine E.”
Reducing autocorrelation times in lattice simulations with generative adversarial networks
Pawlowski, J. M., & Urban, J. M. (2020) · Machine Learning Science and Technology · doi:10.1088/2632-2153/abae73 · Cited by 86
Single image super-resolution with denoising diffusion GANS
Xiao, H., Wang, X., Wang, J., Cai, J., Deng, J.-H., Yan, J.-K., & Tang, Y.-D. (2024) · Scientific Reports · doi:10.1038/s41598-024-52370-3 · Cited by 70
“In adversarial training, the approach is akin to the training process of most GANs.”
MethodInfluentialCross-disciplinary perspectives on the potential for artificial intelligence across chemistry
Mroz, A. M., Basford, A. R., Hastedt, F., Jayasekera, I. S., Mosquera‐Lois, I., Sedgwick, R., Ballester, P. J., Bocarsly, J. D., del Rio‐Chanona, E. A., Evans, M. L., et al. (2025) · Chemical Society Reviews · doi:10.1039/d5cs00146c · Cited by 72
A Reliable Generative Adversarial Network Approach for Climate Downscaling and Weather Generation
Rampal, N., Gibson, P. B., Sherwood, S. C., Abramowitz, G., & Hobeichi, S. (2025) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2024ms004668 · Cited by 81
“…implicitly learning through a powerful loss function that goes beyond traditional pixel‐wise comparisons and can improve the generator's ability to produce outputs that are more similar to real data in terms of both distribution and spatial structure (Gui et al., 2023; Gulrajani et al., 2017).”
Enhanced GAN-Based Joint Wind-Solar-Load Scenario Generation With Extreme Weather Labelling
Wang, H., Qin, B., Hong, S., Xu, X., Su, Y., Lu, T., & Ding, T. (2025) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2025.3573166 · Cited by 58
“The current research work on GAN mainly focuses on the above problems, and improves the model structure and model training process [37].”
Within-Modality Synthesis and Novel Radiomic Evaluation of Brain MRI Scans
Rezaeijo, S. M., Chegeni, N., Naeini, F. B., Makris, D., & Bakas, S. (2023) · Cancers · doi:10.3390/cancers15143565 · Cited by 59
“literature [23], albeit no consensus has been reached on an optimal evaluation metric for a particular domain.”
BackgroundAdvMIL: Adversarial multiple instance learning for the survival analysis on whole-slide images
Liu, P., Ji, L., Ye, F., & Fu, B. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.103020 · Cited by 75
Image forgery detection: comprehensive review of digital forensics approaches
Singh, S. P., & Kumar, R. (2024) · Journal of Computational Social Science · doi:10.1007/s42001-024-00265-8 · Cited by 65
“It was developed by Ian Goodfellow in 2014 [38].”
Generative adversarial networks for transition state geometry prediction
Makoś, M. Z., Verma, N., Larson, E. C., Freindorf, M., & Kraka, E. (2021) · The Journal of Chemical Physics · doi:10.1063/5.0055094 · Cited by 66
Multi-Label Clinical Time-Series Generation via Conditional GAN
Lu, C. H., Reddy, C. K. A., Wang, P., Nie, D., & Ning, Y. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3310909 · Cited by 79
“Compared with conventional generative models such as autoencoder and variational autoencoder [18], [19], [20], GANs are able to generate more realistic data [21].”
BackgroundSeven HCI Grand Challenges Revisited: Five-Year Progress
Stephanidis, C., Salvendy, G., Antona, M., Duffy, V. G., Gao, Q., Karwowski, W., Konomi, S., Nah, F. F., Ntoa, S., Rau, P. P., et al. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2450411 · Cited by 69
“The digital content used to train generative AI includes but is not limited to videos, audio, images, and text (Abukmeil et al., 2022; Gui et al., 2023).”
Generative adversarial networks and their application to 3D face generation: A survey
Toshpulatov, M. A., Lee, W., & Lee, S. (2021) · Image and Vision Computing · doi:10.1016/j.imavis.2021.104119 · Cited by 63
EnerGAN++: A Generative Adversarial Gated Recurrent Network for Robust Energy Disaggregation
Kaselimi, M., Doulamis, N. D., Voulodimos, A. S., Doulamis, A. D., & Protopapadakis, E. E. (2020) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2020.3045829 · Cited by 62
“Probabilistic generative models demonstrate excellent performance for various tasks such as denoising, inpainting, texture synthesis, video and natural language processing [44].”
BackgroundThe Development and Application of Machine Learning in Atmospheric Environment Studies
Zheng, L., Lin, R., Wang, X., & Chen, W. (2021) · Remote Sensing · doi:10.3390/rs13234839 · Cited by 60
DR-GAN: Distribution Regularization for Text-to-Image Generation
Tan, H., Liu, X., Yin, B., & Li, X. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3165573 · Cited by 63
“Just like GAN’s theory [8], a strong discriminator is not conducive to generator optimization.”
BackgroundInfluentialControlled generation of unseen faults for Partial and Open-Partial domain adaptation
Rombach, K., Michau, G., & Fink, O. (2022) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2022.108857 · Cited by 58
“Controlled Synthetic Data Generation has raised a lot of attention in recent years [36], especially in the field of computer vision.”
BackgroundAn in-depth review and analysis of mode collapse in generative adversarial networks
Barsha, F. L., & Eberle, W. (2025) · Machine Learning · doi:10.1007/s10994-025-06772-7 · Cited by 69
“In 2021, Gui et al. (2021) presented a detailed review of different GAN variants, including algorithms, theory, applications, theoretical concerns, and future research prospects.”
A Comprehensive Survey on Self-Supervised Learning for Recommendation
Ren, X., Wei, W., Xia, L., & Huang, C. (2025) · ACM Computing Surveys · doi:10.1145/3746280 · Cited by 79
“What sets adversarial learning apart from reconstructive learning is the inclusion of a discriminator Ω (·) , which determines whether a given sample is real or generated [28, 43].”
Wang, M., Lin, T., Lin, A., Yu, K., Peng, Y., Wang, L., Chen, C., Zou, K., Liang, H., Chen, M., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-60577-9 · Cited by 93
“Generative Adversarial Networks (GANs) or diffusion models can create realistic fundus images that mirror rare disease appearances, thereby expanding the sample diversity and allowing the network to learn clinically important features that are otherwise scarce [32, 33].”
Weld crack detection and quantification using laser thermography, mask R-CNN, and CycleGAN
Kim, C., Hwang, S., & Hoon Sohn, A. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104568 · Cited by 55
Balasubramanian, P., Liyana, S., Sankaran, H., Sivaramakrishnan, S., Pusuluri, S., Pirttikangas, S., & Peltonen, E. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11338-z · Cited by 78
Liu, X., Teng, W., Wu, S., Wu, X., Liu, Y., & Ma, Z. (2021) · Measurement · doi:10.1016/j.measurement.2021.109810 · Cited by 53
Pseudo Labels for Unsupervised Domain Adaptation: A Review
Li, Y., Guo, L., & Ge, Y. (2023) · Electronics · doi:10.3390/electronics12153325 · Cited by 51
Toward the end-to-end optimization of particle physics instruments with differentiable programming
Dorigo, T., GIAMMANCO, A., Vischia, P., Aehle, M., Bawaj, M., Boldyrev, A. S., Manzano, P. D. C., Деркач, Д., Donini, J., Edelen, A. L., et al. (2023) · Reviews in Physics · doi:10.1016/j.revip.2023.100085 · Cited by 89
Acar, E., Şahin, E., & Yılmaz, İ. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06344-5 · Cited by 52
“Examples of data generation with GANs include text-toimage synthesis, superimage resolution, style transfer and symbolic music production [30].”
BackgroundGANBOT: a GAN-based framework for social bot detection
Najari, S., Salehi, M., & Farahbakhsh, R. (2021) · Social Network Analysis and Mining · doi:10.1007/s13278-021-00800-9 · Cited by 57
Brain-Inspired Learning, Perception, and Cognition: A Comprehensive Review
Jiao, L., Ma, M., He, P., Geng, X., Liu, X., Liu, F., Ma, W., Yang, S., Hou, B., & Tang, X. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3401711 · Cited by 62
“Related review articles include the GANs’ tutorial [159], research [160], and review [161] from the perspectives of the loss function, neural network architecture, regularization, and normalization, and the latest development of GAN [162].”
Ambreen, S., Umar, M., Noor, A., Jain, H., & Ali, R. (2024) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2024.117164 · Cited by 53
Roy, A., Hussain, A., Sharma, P., Balasubramanian, G., Taufique, M. F. N., Devanathan, R., Singh, P. K., & Johnson, D. D. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4266764 · Cited by 56
Atia, N., Benzaoui, A., Jacques, S., Hamiane, M., Kourd, K. E., Bouakaz, A., & Ouahabi, A. (2022) · Cancers · doi:10.3390/cancers14184399 · Cited by 52
Faster diffusion model with improved quality for particle cloud generation
Leigh, M., Sengupta, D., Raine, J. A., Quétant, G., & Golling, T. (2024) · Physical review. D/Physical review. D. · doi:10.1103/physrevd.109.012010 · Cited by 58
Graphic Design Education in the Era of Text‐to‐Image Generation: Transitioning to Contents Creator
Hwang, Y., & Wu, Y. (2025) · International Journal of Art & Design Education · doi:10.1111/jade.12558 · Cited by 47
Gridtopo-GAN for Distribution System Topology Identification
Wu, H., Xu, Z., Zhao, J., & Chai, S. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3158614 · Cited by 47
“GAN has a powerful capacity for generative tasks with many successful applications [31], such as image superresolution, face syntheses, language processing, and protein binding optimization.”
BackgroundSynthetic electronic health records generated with variational graph autoencoders
Nikolentzos, G., Vazirgiannis, M., Xypolopoulos, C., Lingman, M., & Brandt, E. G. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00822-x · Cited by 65
“Variational Autoencoders (VAEs) [22, 23] – and their off-spring graph variational autoencoders [36, 34, 8] – and Generative Adversarial Networks (GANs) [13, 16] are recent deep learning architectures of particular promise.”
BackgroundGupta, S., Kumar, A., & Maiti, J. (2024) · Safety Science · doi:10.1016/j.ssci.2024.106590 · Cited by 54
On The Philosophy of Unsupervised Learning
Watson, D. (2022) · Philosophy & Technology · doi:10.1007/s13347-023-00635-6 · Cited by 53
“Many variations exist—for overviews, see Creswell et al. (2018) and Gui et al. (2021)—but the unifying idea behind them all is a zero-sum game between two networks, a generator f and a discriminator g .”
BackgroundZeroualı, B., Bailek, N., Tariq, A., Kuriqi, A., Guermoui, M., Alharbi, A. H., Khafaga, D. S., & El‐kenawy, E. M. (2024) · Scientific Reports · doi:10.1038/s41598-024-72588-5 · Cited by 48
Bibri, S. E., & Huang, J. (2025) · Sustainable Cities and Society · doi:10.1016/j.scs.2025.106826 · Cited by 57
Image2Reverb: Cross-Modal Reverb Impulse Response Synthesis
Singh, N., Mentch, J., Ng, J., Beveridge, M., & Drori, I. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00035 · Cited by 46
“In this work we model IR generation as a cross-modal paired-example domain adaptation problem and apply a conditional GAN [10, 12, 25] to synthesize plausible audio impulse responses conditioned on images of spaces.”
MethodInfluentialTextControlGAN: Text-to-Image Synthesis with Controllable Generative Adversarial Networks
Ku, H., & Lee, M. (2023) · Applied Sciences · doi:10.3390/app13085098 · Cited by 52
“GANs have been expanded in various domains [6,15,16], including image and video processing as well as image translation, voice signals, 3D rendering, and natural language processing [17–24].”
BackgroundComparison of tabular synthetic data generation techniques using propensity and cluster log metric
Pathare, A. A., Mangrulkar, R., Suvarna, K., Parekh, A., Thakur, G., & Gawade, A. U. (2023) · International Journal of Information Management Data Insights · doi:10.1016/j.jjimei.2023.100177 · Cited by 64
Amrouni, N., Benzaoui, A., & Zeroual, A. (2023) · Applied Sciences · doi:10.3390/app14010153 · Cited by 45
A Comprehensive Survey on Deep Learning-based Predictive Maintenance
Khan, U., Cheng, D. S., Setti, F., Fummi, F., Cristani, M., & Capogrosso, L. (2025) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3732287 · Cited by 67
Chen, Q., Cui, Z., Liu, G., Yang, Z., & Ma, X. (2022) · Journal of Hydrology · doi:10.1016/j.jhydrol.2022.127970 · Cited by 44
Multiround Transfer Learning and Modified Generative Adversarial Network for Lung Cancer Detection
Chui, K. T., Gupta, B. B., Jhaveri, R. H., Chi, H. R., Arya, V., Almomani, A., & Nauman, A. (2023) · International Journal of Intelligent Systems · doi:10.1155/2023/6376275 · Cited by 55
Gao, K., Yu, A., You, X., Qiu, C., & Liu, B. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3271392 · Cited by 57
“However, it is undeniable that the process of adversarial training is a very tricky issue due to the instability and the difficulty of convergence [39].”
BackgroundChang, C., Peng, J., Safari, M., Salari, E., Pan, S., Roper, J. R., Qiu, R. L. J., Gao, Y., Shu, H. G., Mao, H. Z., et al. (2024) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ad209c · Cited by 58
Shi, H., Fang, L.-R., Chen, X.-Y., Gu, C.-H., Ma, K., Zhang, X.-S., Zhang, Z., Gu, J.-P., & Lim, E.-G. (2024) · IET Smart Grid · doi:10.1049/stg2.12191 · Cited by 46
“Second, mechanisms of robust ML and game theory [241] are adopted to provide frameworks for creating systems.”
Jie, Y., Xu, Y., Li, X., Zhou, F., Lv, J., & Li, H. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103146 · Cited by 50
“In addition, GAN-based methods often face issues such as mode collapse and training instability [29].”
Prabhat, NISHANT, N., & Vishwakarma, D. K. (2020) · International Conference on Intelligent Computing and Control Systems (ICICCS) · doi:10.1109/iciccs48265.2020.9121178 · Cited by 44
Arar, K., Tlili, A., Schunka, L., Salha, S., & Saiti, A. (2025) · Leadership and Policy in Schools · doi:10.1080/15700763.2025.2451982 · Cited by 43
“Therefore, by speeding up data collection, processing, analysis, and interpretation, the use of AI could enable more informed decision-making than would otherwise be feasible (Ali et al., 2024; Gui et al., 2023).”
Applications of generative adversarial networks in materials science
Jiang, Y., Li, J., Yang, X., & Yuan, R. (2024) · Materials Genome Engineering Advances · doi:10.1002/mgea.30 · Cited by 54
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.