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 201–300 of 1,002
AI-driven de novo enzyme design: Strategies, applications, and future prospects
Cui, X.-C., Zheng, Y., Liu, Y., Yuchi, Z., & Yuan, Y. (2025) · Biotechnology Advances · doi:10.1016/j.biotechadv.2025.108603 · Cited by 47
ChemPix: automated recognition of hand-drawn hydrocarbon structures using deep learning
Weir, H., Thompson, K. C., Woodward, A., Choi, B., Braun, A., & Martínez, T. J. (2021) · Chemical Science · doi:10.1039/d1sc02957f · Cited by 53
“Generative adversarial networks (GANs) have become popular in recent years for generating high quality synthetic data.(64-65) GANs were first introduced by Goodfellow et al.”
BackgroundQuaternion Generative Adversarial Networks
Grassucci, E., Cicero, E., & Comminiello, D. (2022) · Intelligent systems reference library · doi:10.1007/978-3-030-91390-8_4 · Cited by 43
“The two terms in the objective are two cross-entropies [14].”
BackgroundTalking human face generation: A survey
Toshpulatov, M. A., Lee, W., & Lee, S. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119678 · Cited by 47
Zhao, P., Ding, Z., Li, Y., Zhang, X., Zhao, Y., Wang, H., & Yang, Y. (2024) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2024.111141 · Cited by 50
Tian, M., Chen, B., Guo, A., Jiang, S., & Zhang, A. R. (2024) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocae229 · Cited by 81
Jiang, C., Zhao, J., Ding, Y., & Li, G. (2023) · Sensors · doi:10.3390/s23073686 · Cited by 48
“In other words, G and D play games with each other and eventually reach a “Nash equilibrium” in the best case, where the generated data cannot be discriminated from the real data [55].”
BackgroundBayesian conditional diffusion models for versatile spatiotemporal turbulence generation
Gao, H., Han, X., Fan, X., Sun, L., Liu, L., Duan, L., & Wang, J. (2024) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2024.117023 · Cited by 83
Confucius tri-learning: A paradigm of learning from both good examples and bad examples
Ren, P., Han, Z., Yu, Z., & Zhang, B. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111481 · Cited by 43
Ye, Y., Strong, M., Lou, Y., Faulkner, C. A., Zuo, W., & Upadhyaya, S. (2022) · Energy and Buildings · doi:10.1016/j.enbuild.2022.112247 · Cited by 41
“Recently, hundreds of variations of GANs have been proposed to address the limitations of the original GAN model [22], including models with the ability to generate samples for multiple classes.”
BackgroundAssessing the Ability of Generative Adversarial Networks to Learn Canonical Medical Image Statistics
Kelkar, V. A., Gotsis, D. S., Brooks, F. J., Prabhat, K. C., Myers, K. J., Zeng, R., & Anastasio, M. A. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3241454 · Cited by 55
DPWGAN: High-Quality Load Profiles Synthesis With Differential Privacy Guarantees
Huang, J., Huang, Q., Mou, G., & Wu, C. (2022) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2022.3230671 · Cited by 56
“In the past few years, GAN algorithms have been consistently showing their capabilities of generating high-quality synthetic data [26], [27], [28], meanwhile yielding varieties of applications [29].”
BackgroundDeep Representation Learning: Fundamentals, Technologies, Applications, and Open Challenges
Payandeh, A., Baghaei, K. T., Fayyazsanavi, P., Ramezani, S. B., Chen, Z., & Rahimi, S. (2023) · IEEE Access · doi:10.1109/access.2023.3335196 · Cited by 64
“Existing surveys have focused on specific approaches such as autoencoders [48], [49], generative adversarial networks [50], and foundation models [51].”
BackgroundLeveraging GANs data augmentation for imbalanced medical image classification
Ding, H., Huang, N., & Cui, X. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112050 · Cited by 48
Low-light image enhancement using generative adversarial networks
Wang, L., Zhao, L., Zhong, T., & Wu, C. (2024) · Scientific Reports · doi:10.1038/s41598-024-69505-1 · Cited by 52
“GANs comprise generators and discriminators that are trained through adversarial learning to generate images that are more closely aligned with the actual results 28 .”
BackgroundEmerging SMOTE and GAN Variants for Data Augmentation in Imbalance Machine Learning Tasks: A Review
Udu, A. G., Salman, M. T., Ghalati, M. K., Lecchini, A., Siddle, D. R., & Dong, H. (2025) · IEEE Access · doi:10.1109/access.2025.3584532 · Cited by 56
“GAN-based methods have shown advantages over SMOTE-based variants in modelling complex or multi-modal class distributions, particularly in high-dimensional or unstructured datasets [9], [72], [105], [111].”
Lehmhus, D. (2024) · Metals · doi:10.3390/met14030334 · Cited by 50
Application of deep learning in laser-induced breakdown spectroscopy: a review
Zhang, C., Zhou, L., Liu, F., Huang, J., & Peng, J. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10590-5 · Cited by 41
“Upon training, the GAN is intended to produce believable synthetic data, thus expanding the dataset for model training (Aggarwal et al. 2021a; Gui et al. 2021).”
MethodTu, Z., Yang, X., He, X. G., Yan, J., & Xu, T. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3359095 · Cited by 57
“Moreover, some GAN-based methods [43] adopt more measures during adversarial training, such as the Wasserstein distances [44], [45], to achieve more visual improvements.”
MethodMachine Learning in Petrology: State-of-the-Art and Future Perspectives
Petrelli, M. (2024) · Journal of Petrology · doi:10.1093/petrology/egae036 · Cited by 55
Zhang, Z., Jin, H., Zheng, Z., Sharma, A., Wang, L., Pramanik, M., & Zheng, Y. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3192072 · Cited by 40
“The above optimization problem can be solved with min-max game under the Generative Adversarial Network (GAN) framework, which can be quantitatively supported by following mathematical formulas [47].”
BackgroundArtificial intelligence methods for modeling gasification of waste biomass: a review
Alfarra, F., Özcan, H., Cihan, P., Öngen, A., Güvenç, S. Y., & Ciner, M. N. (2024) · Environmental Monitoring and Assessment · doi:10.1007/s10661-024-12443-2 · Cited by 41
“The utilization of GANs for analyzing time series data is a promising solution to several challenges encountered by existing dataset custodians, which have remained unaddressed by alternative machine learning or regression methodologies (Gui et al., 2023).”
Ross, N. S., Mashinini, P. M., Shibi, C. S., Gupta, M. K., Korkmaz, M. E., Królczyk, G., & Sharma, V. S. (2024) · Measurement · doi:10.1016/j.measurement.2024.114515 · Cited by 44
VAE-WACGAN: An Improved Data Augmentation Method Based on VAEGAN for Intrusion Detection
Tian, W., Shen, Y., Guo, N., Yuan, J., & Yang, Y. (2024) · Sensors · doi:10.3390/s24186035 · Cited by 44
“Generative Adversarial Networks (GANs) [24] are a type of generative model that have achieved significant results in image generation [25].”
BackgroundInformation Cascade Popularity Prediction via Probabilistic Diffusion
Cheng, Z., Zhou, F., Xu, X., Zhang, K., Trajcevski, G., Zhong, T., & Yu, P. S. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3465241 · Cited by 60
“On the one hand, although current generative models can generate the distribution in a sequence-to-sequence manner [18], [19], they still face instability during optimization [16] and posterior collapse issues [17].”
BackgroundRizvi, S. K. J., Azad, M. A., & Fraz, M. M. (2021) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-021-09543-4 · Cited by 37
Jiao, J., & Cao, X. (2024) · Frontiers in Psychology · doi:10.3389/fpsyg.2024.1450717 · Cited by 37
“Generative adversarial networks (GAN) are one of the most widely applied AI technologies in design (Gui et al., 2020), which are frequently integrated into supporting tools of design to generate inspiration, such as in designing the user interface (UI) (Mozaffari et al., 2022; Bunian et al., 2021),…”
BackgroundJin, H., Yu, C.-S., Gong, Z., Zheng, R., Zhao, Y., & Fu, Q. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.104104 · Cited by 44
Data augmentation in material images using the improved HP-VAE-GAN
Han, Y., Liu, Y., & Chen, Q. (2023) · Computational Materials Science · doi:10.1016/j.commatsci.2023.112250 · Cited by 42
Li, Q., Zhang, W., Chen, F., Huang, G., Wang, X., Yuan, W., & Xiong, X. (2024) · Nuclear Engineering and Technology · doi:10.1016/j.net.2024.02.056 · Cited by 36
MAG-GAN: Massive attack generator via GAN
Chen, J., Zheng, H., Xiong, H., Shen, S., & Su, M. (2020) · Information Sciences · doi:10.1016/j.ins.2020.04.019 · Cited by 41
Deep learning powers cancer diagnosis in digital pathology
He, Y., Zhao, H. P., & Wong, S. T. C. (2020) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2020.101820 · Cited by 40
“…there are diversification of tasks, such as RNN-based time series deep learning model [18–21], used for image generation generative adversarial networks (GANs) [22–32], object detection models [33–35], natural language processing (NLP) models [36–40], and reinforcement learning models [41–43].”
BackgroundKim, J., Kim, T., & Ryu, J.-G. (2023) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2023.103312 · Cited by 50
Policy-based optimization: single-step policy gradient method seen as an evolution strategy
Viquerat, J., Duvigneau, R., Méliga, P., Kuhnle, A., & Hachem, E. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07779-0 · Cited by 41
“astonishing performance levels in a variety of tasks such as image classification [1, 2], speech recognition [3] or generative tasks [4], to name a few.”
BackgroundBlind Image Restoration Based on Cycle-Consistent Network
Wu, S., Dong, C., & Qiao, Y. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3139209 · Cited by 42
“Several methods [23], [24] try to synthesize paired training data,”
MethodA surface defect detection system for golden diamond pineapple based on CycleGAN and YOLOv4
Chen, S., Lai, Y.-W., Kuo, C.-L., Lo, C.-Y., Lin, Y.-S., Lin, Y.-R., Kang, C.-H., & Tsai, C.-C. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2022.07.018 · Cited by 36
Mask-Aware Pseudo Label Denoising for Unsupervised Vehicle Re-Identification
Lu, Z., Lin, R., He, Q., & Hu, H. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3233565 · Cited by 37
“Generative Adversarial Networks (GANs) [21] and feature space adaptation [22], [23], [24], [25].”
BackgroundAssessing Deep Generative Models in Chemical Composition Space
Türk, H., Landini, E., Künkel, C., Margraf, J. T., & Reuter, K. (2022) · Chemistry of Materials · doi:10.1021/acs.chemmater.2c01860 · Cited by 42
Quantum semi-supervised generative adversarial network for enhanced data classification
Nakaji, K., & Yamamoto, N. (2021) · Scientific Reports · doi:10.1038/s41598-021-98933-6 · Cited by 47
“As in the case of standard GAN, the SGAN [30–33] consists of a generator and a discriminator, but the role of discriminator is to discriminate real/fake of the input data plus to estimate its label; that is, the goal of SGAN is to train the discriminator so that it becomes a good classifier, rather…”
BackgroundGenerative Adversarial Networks in Human Emotion Synthesis: A Review
Hajarolasvadi, N., Ramírez, M. A., Beccaro, W., & Demirel, H. (2020) · IEEE Access · doi:10.1109/access.2020.3042328 · Cited by 42
Situ, Z., Teng, S., Liu, H., Luo, J., & Zhou, Q. (2021) · IEEE Access · doi:10.1109/access.2021.3073915 · Cited by 38
“In order to enhance data quantity and quality, data augmentation technique based on the state-of-the-art unsupervised Generative Adversarial Networks (GANs) has been developed [16]–[18].”
MethodKumar, L., & Singh, D. K. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15138-x · Cited by 44
“We have discussed below some approaches for this synthesis process. a. Vanilla GAN Vanilla GAN [29] is the simplest generative model that is used for the Image-to-Video synthesis process.”
RetractedWang, Y., Zhang, Q., Wang, G., & Cheng, H. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10818-y · Cited by 40
Deep generative models in energy system applications: Review, challenges, and future directions
Zhang, X., Glaws, A., Cortiella, A., Emami, P., & King, R. (2024) · Applied Energy · doi:10.1016/j.apenergy.2024.125059 · Cited by 46
Shahzad, M. F., Xu, S., An, X., Zahid, H., & Asif, M. (2025) · European Journal of Education · doi:10.1111/ejed.70050 · Cited by 44
Generative AI for computational chemistry: A roadmap to predicting emergent phenomena
Tiwary, P., Herron, L., John, R., Lee, S., Sanwal, D., & Wang, R. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2415655121 · Cited by 42
Yıldız, E., Arslan, A. T., Taş, A. Y., Acer, A. F., Demir, S., Şahin, A., & Barkana, D. E. (2021) · Translational Vision Science & Technology · doi:10.1167/tvst.10.6.33 · Cited by 37
Chai, Y., Liu, H., Xu, J., Samtani, S., Jiang, Y., & Liu, H. (2022) · ACM Transactions on Management Information Systems · doi:10.1145/3561653 · Cited by 36
“As a result, both networks improve themselves in this game [Gui et al. 2021].”
BackgroundLiang, Z., Zheng, Z., Chen, W., Pei, Z., Wang, J., & Chen, J. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106311 · Cited by 37
Quantum integration of elementary particle processes
Agliardi, G., Grossi, M., Pellen, M., & Prati, E. (2022) · Physics Letters B · doi:10.1016/j.physletb.2022.137228 · Cited by 52
Wang, C., Liu, J., & Zio, E. (2022) · Journal of Dynamics Monitoring and Diagnostics · doi:10.37965/jdmd.2022.68 · Cited by 32
“In the current use of GAN for fault diagnosis, convolution and deconvolution layers are widely adopted for tackling high-frequency monitoring data [35].”
BackgroundMethodInfluentialGao, S., Wan, C., Zhou, Z., Hou, J., Xie, L., & Xue, S. (2023) · Structures · doi:10.1016/j.istruc.2023.105277 · Cited by 32
Generative machine learning methods for multivariate ensemble postprocessing
Chen, J., Janke, T., Steinke, F., & Lerch, S. (2024) · The Annals of Applied Statistics · doi:10.1214/23-aoas1784 · Cited by 71
“While impressive results have been achieved by GANs, in particular in the context of image processing and computer vision, the adversarial training process is often considered to be complex and unstable (Gui et al., 2021).”
BackgroundYang, C., Li, H., Cao, S., Zhang, K., Xiang, W., & Liu, X. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102605 · Cited by 32
Synergistic integration of metaheuristics and machine learning: latest advances and emerging trends
Zhang, R., Wang, J., Liu, C., Su, K., Ishibuchi, H., & Jin, Y. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11266-y · Cited by 36
Gong, D. (2020) · International Journal of Advanced Trends in Computer Science and Engineering · doi:10.30534/ijatcse/2020/58932020 · Cited by 37
Discrete Haze Level Dehazing Network
Cong, X., Gui, J., Miao, K., Zhang, J., Wang, B., & Chen, P. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413876 · Cited by 32
Self-citationYang, C., Zhang, J., & Han, J. (2020) · Proceedings · doi:10.1109/icdm50108.2020.00081 · Cited by 31
Multimodal Approach for DeepFake Detection
Lomnitz, M., Hampel-Arias, Z., Sandesara, V., & Hu, S. (2020) · 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) · doi:10.1109/aipr50011.2020.9425192 · Cited by 30
Artifact Detection and Restoration in Histology Images With Stain-Style and Structural Preservation
Ke, J., Liu, K., Sun, Y., Yuying, X., Huang, J., Lu, Y., Dai, J., Chen, Y., Han, X., Shen, Y., et al. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3288940 · Cited by 33
“This setting reduced training oscillation in most of prevalent GANs [64], and the image buffer number was set to 50.”
BackgroundAi, X., Smith, M. C., & Feltus, F. A. (2023) · Computational and Systems Oncology · doi:10.1002/cso2.1050 · Cited by 40
A Collaborative Self-Supervised Domain Adaptation for Low-Quality Medical Image Enhancement
Hou, Q., Wang, Y., Cao, P., Cheng, S., Lan, L., Yang, J., Liu, X., & Zai͏̈ane, O. R. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3367367 · Cited by 33
Yigin, B., & Çelik, M. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12030493 · Cited by 34
Liang, J., Sadiq, M., Yang, G., Jiang, K., Cai, T., & Ma, M. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108862 · Cited by 35
Data efficiency assessment of generative adversarial networks in energy applications
Nabila, U. M., Lin, L., Zhao, X., Gurecky, W., Ramuhalli, P., & Radaideh, M. I. (2025) · Energy and AI · doi:10.1016/j.egyai.2025.100501 · Cited by 30
A Review of Deepfake and Its Detection: From Generative Adversarial Networks to Diffusion Models
Liu, B., Liu, B., Zhu, T., & Ding, M. (2025) · International Journal of Intelligent Systems · doi:10.1155/int/9987535 · Cited by 40
Jiang, P., Ma, Z., & Mei, G. (2026) · Natural hazards and earth system sciences · doi:10.5194/nhess-26-487-2026 · Cited by 43
Behzadi, M. M., & Ilieş, H. (2021) · Journal of Mechanical Design · doi:10.1115/1.4052757 · Cited by 38
Single and Combined Neuroimaging Techniques for Alzheimer’s Disease Detection
Amini, M., Pedram, M. M., Moradi, A., Jamshidi, M., & Ouchani, M. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/9523039 · Cited by 33
Conditional Wasserstein generative adversarial networks applied to acoustic metamaterial design
Lai, P. C.-C., Amirkulova, F., & Gerstoft, P. (2021) · The Journal of the Acoustical Society of America · doi:10.1121/10.0008929 · Cited by 36
“GANs were described by Yann LeCun, Director of AI Research at Facebook, as “the most interesting idea in the last 10 years in ML.” 89 The conditional GAN 46 was introduced which can learn single-modal and multi-modal models.”
Image Generation and Recognition for Railway Surface Defect Detection
Xia, Y., Han, S. W., & Kwon, H. (2023) · Sensors · doi:10.3390/s23104793 · Cited by 32
“When the loss function reaches a balance, the discriminator cannot distinguish between real and synthetic defects [11,12].”
BackgroundMachine learning meets physics: A two-way street
Levine, H., & Tu, Y. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2403580121 · Cited by 37
Hui, M., & Li, N. (2024) · IEEE Access · doi:10.1109/access.2024.3441088 · Cited by 39
“Its quintessential characteristic is the ability to produce diverse data types, including text, images, and audio, transcending mere analysis and categorization of pre-existing data [1].”
BackgroundMulti-label domain adversarial reinforcement learning for unsupervised compound fault recognition
Wang, Z., Xuan, J., Shi, T., & Li, Y. (2024) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2024.110638 · Cited by 32
Xia, Y., Cheng, X., & Hu, X. F. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110164 · Cited by 29
Explainable deepfake detection across different modalities: An overview of methods and challenges
Momin, M. S., Sufian, A., Barman, D., Leo, M., Distante, C., & Damer, N. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105738 · Cited by 37
From rumor to genetic mutation detection with explanations: a GAN approach
Cheng, M., Li, Y., Nazarian, S., & Bogdan, P. (2021) · Scientific Reports · doi:10.1038/s41598-021-84993-1 · Cited by 30
An unsupervised domain adaptation model based on dual-module adversarial training
Yang, Y., Zhang, T., Li, G., Kim, T., & Wang, G. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.12.060 · Cited by 29
“In addition to the adversarial training method based on GRL, there are many other adversarial training methods based on generative adversarial nets (GANs) [15, 32, 52, 22, 17].”
MethodAugmented Multimodality Fusion for Generalized Zero-Shot Sketch-Based Visual Retrieval
Jing, T., Xia, H., Hamm, J., & Ding, Z. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3173815 · Cited by 31
Reliable Detection of Location Spoofing and Variation Attacks
Kim, C., Chang, S., Lee, D., Kim, J., Park, K., & Kim, J. (2023) · IEEE Access · doi:10.1109/access.2023.3241236 · Cited by 30
“In this section, we present our approach to zero-day detection, given the emergence of new types of spoofing attacks with smarter features to fool the detector (e.g., using a generative model like generative adversarial networks [30]).”
Conditional Sampling with Monotone GANs: From Generative Models to Likelihood-Free Inference
Baptista, R., Hosseini, B., Kovachki, N., & Marzouk, Y. (2024) · SIAM/ASA Journal on Uncertainty Quantification · doi:10.1137/23m1581546 · Cited by 84
Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket PerspectivePreprint
Chen, T., Cheng, Y., Gan, Z., Liu, J., & Wang, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.00397 · Cited by 73
“GANs [22] have gained popularity in diverse computer vision scenarios.”
BackgroundLearning cortical representations through perturbed and adversarial dreaming
Deperrois, N., Petrovici, M. A., Senn, W., & Jordan, J. (2022) · eLife · doi:10.7554/elife.76384 · Cited by 28
“Note that, in principle, LGAN can be any GAN-specific loss function (Gui et al., 2020).”
Hao, Y., Li, X., & Zhang, C. (2023) · Analytica Chimica Acta · doi:10.1016/j.aca.2023.341763 · Cited by 28
Image Synthesis Under Limited Data: A Survey and Taxonomy
Yang, M., & Wang, Z. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02357-y · Cited by 39
“Although there are already some other surveys that discuss the developments, main challenges, potential applications, and future opportunities of deep generative models [55], [56], [57], [58], [59], very few have focused on the development of deep generative models in limited data scenarios.”
Application of Deep Learning Technology in Monitoring Plant Attribute Changes
Han, S., & Wang, H. (2025) · Sustainability · doi:10.3390/su17177602 · Cited by 36
Generative Adversarial Network Synthesis of Hyperspectral Vegetation Data
Hennessy, A., Clarke, K. D., & Lewis, M. M. (2021) · Remote Sensing · doi:10.3390/rs13122243 · Cited by 31
Generative adversarial networks in ophthalmology: what are these and how can they be used?
Wang, Z., Lim, G., Ng, W. Y., Keane, P. A., Campbell, J. P., Tan, G. S. W., Schmetterer, L. F., Wong, T. Y., Liu, Y., & Ting, D. S. W. (2021) · Current Opinion in Ophthalmology · doi:10.1097/icu.0000000000000794 · Cited by 32
TSA-GAN: A Robust Generative Adversarial Networks for Time Series Augmentation
Zheng, L., Ma, C., Shi, X., Zhang, D., Li, W., & Wu, L. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534001 · Cited by 33
Data/Model Jointly Driven High-Quality Case Generation for Power System Dynamic Stability Assessment
Zhu, L., & Hill, D. J. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3123823 · Cited by 29
García-Vicente, C., Chushig-Muzo, D., Mora-Jiménez, I., Fabelo, H. A., Gram, I. T., Løchen, M., Granja, C., & Soguero-Ruíz, C. (2023) · Applied Sciences · doi:10.3390/app13074119 · Cited by 36
Parrott, C. M., Abueidda, D., & James, K. A. (2023) · Journal of Mechanical Design · doi:10.1115/1.4056929 · Cited by 27
Multilingual Hate Speech Detection: A Semi-Supervised Generative Adversarial Approach
Mnassri, K., Farahbakhsh, R., & Crespi, N. (2024) · Entropy · doi:10.3390/e26040344 · Cited by 46
Lightweight diffusion models: a survey
Song, W., Ma, W., Zhang, M., Zhang, Y., & Zhao, X. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10800-8 · Cited by 40
Tan, H., Zhang, Z., Li, Y., Shi, X., Wang, L., Yang, X., & Zhou, F. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3458980 · Cited by 31
“Besides, training generative networks is typically time-consuming and unstable [36].”
scMoMtF: An interpretable multitask learning framework for single-cell multi-omics data analysis
Lan, W., Ling, T., Chen, Q., Zheng, R., Li, M., & Pan, Y. F. (2024) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1012679 · Cited by 30
Artificial Intelligence and Generative Models for Materials Discovery: A Review
Handoko, A. D., & Made, R. I. (2025) · World Scientific Annual Review of Functional Materials · doi:10.1142/s2810922825400018 · Cited by 42
When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
Zhang, C., Wang, J., Yen, G. G., Zhao, C., Sun, Q., Tang, Y. S., Qian, F., & Kurths, J. (2020) · Patterns · doi:10.1016/j.patter.2020.100050 · Cited by 30
Zhang, X., Li, H., Tian, X., Chen, C., Su, Y., Li, M., Lv, J., Chen, C., & Lv, X. (2022) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2022.104681 · Cited by 31
Maritime piracy risk assessment and policy implications: A two-step approach
Gong, X., Jiang, H., & Yang, D. (2023) · Marine Policy · doi:10.1016/j.marpol.2023.105547 · Cited by 30
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.