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 501–600 of 1,002
Yu, X., Gu, J., Zhang, X., & Mao, J. (2022) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2022.108535 · Cited by 15
Liu, G., Zhang, L., Wang, Q., & Xu, J. (2022) · Journal of Applied Geophysics · doi:10.1016/j.jappgeo.2022.104846 · Cited by 13
Li, C., Minati, L., Tokgöz, K. K., Fukawa, M., Bartels, J., Sihan, A., Takeda, K.-I., & Ito, H. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3219594 · Cited by 17
“…desirable compared to pattern mixing, as it avoids data corruption in the presence of nonstationarity [36], and compared to generative approaches such as adversarial networks, which have considerable potential but require resource-intensive training to become reliable data generators [37], [38].”
BackgroundGao, C., Li, Z., Ora, H., & Miyake, Y. (2020) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm49941.2020.9313238 · Cited by 14
Dual distribution matching GAN
Zuo, Z., Zhao, L., Li, A., Wang, Z., Chen, H., Xing, W., & Lu, D. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.12.095 · Cited by 13
Pantazis, Y., Paul, D., Fasoulakis, M., Stylianou, Y., & Katsoulakis, M. A. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3161127 · Cited by 21
“Several surveys and reviews on GANs are available in the literature [20]–[23].”
Deep Learning-Based Optimization of Visual–Auditory Sensory Substitution
Kim, M., Park, Y., Moon, K., & Jeong, C. Y. (2023) · IEEE Access · doi:10.1109/access.2023.3243641 · Cited by 12
“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.”
BackgroundBing, Y., Yu, L., Li, S., Cho, Y.-S., & Li, C. (2025) · Journal of Engineering Design · doi:10.1080/09544828.2025.2515553 · Cited by 12
k-SALSA: k-Anonymous Synthetic Averaging of Retinal Images via Local Style Alignment
Jeon, M., Park, H., Kim, H. J., Morley, M., & Cho, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19803-8_39 · Cited by 14
“This is enabled by recent advances in GANs, which intuitively provide a more powerful approach to manipulate images according to their intrinsic manifold [15].”
BackgroundMethodZielinski, C., Winker, M., Aggarwal, R., Ferris, L., Heinemann, M., Lapeña, Jr., Pai, S. A., Ing, E., Citrome, L., Alam, M., et al. (2023) · Open Access Macedonian Journal of Medical Sciences · doi:10.3889/oamjms.2023.11723 · Cited by 12
“Generative AI (GAI) uses generative modeling and advances in deep learning to produce diverse content at scale by utilizing existing media such as text, graphics, audio, and video” [3], [4].”
BackgroundDey, B., Ridder, V. D., Blanco, V., Halder, S., & Waeyenberge, B. V. (2024) · International Symposium ELMAR (ELMAR) · doi:10.1109/elmar62909.2024.10694600 · Cited by 13
“In recent years, significant progress has been made on ML-based image generation [15–18].”
BackgroundGao, Y., Sun, Z., Hu, D., Xie, L., & Ying, Y. B. (2024) · Food Chemistry · doi:10.1016/j.foodchem.2024.141944 · Cited by 12
Self-citationXie, J., Wang, W., Xu, C., Fu, M., & Huang, W. (2024) · International Journal of Pressure Vessels and Piping · doi:10.1016/j.ijpvp.2024.105364 · Cited by 12
Contrastive learning-based multi-view clustering for incomplete multivariate time series
Li, Y., Du, M., Jiang, X., & Zhang, N. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102812 · Cited by 14
Zhong, K., Wu, S., Liu, S., Qi, J., Cheng, L., & Ai, D. (2025) · Journal of Applied Physics · doi:10.1063/5.0268482 · Cited by 12
Deep Learning: Techniques, Taxonomy, Applications, and Future Directions
Sundari, V. M., Rose, R. A. M., Sassirekha, S. M., Nalini, M., Girija, P., & Siva Subramanian, R. (2024) · International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG) · doi:10.1109/icstsdg61998.2024.11026496 · Cited by 12
“GANs have brought a significant change in generative tasks because of their ability to generate good quality and realistic results in areas like image generation, video synthesis and data augmentation[9][10].”
High-Quality Face Sketch Synthesis via Geometric Normalization and Regularization
Li, X., Gao, F., & Huang, F. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428348 · Cited by 12
“Recently, inspired by the great success of Generative Adversarial Networks (GANs) [2, 3] in various image-to-image translation tasks [4], researchers have developed various GAN-based F-SS methods and achieved compelling progress.”
BackgroundTowards AI-Assisted Design Workflows for an Expanded Design Space
Yousif, S., & Vermisso, E. (2022) · Proceedings of the International Conference on Computer-Aided Architectural Design Research in Asia · doi:10.52842/conf.caadria.2022.2.335 · Cited by 12
“Benefitting from the widespread applications of AI, a recent second generation of GDSs is emerging, marking a shift in design, towards an unlimited exploration of the design space, which sometimes becomes a “hyper-dimensional” space, such as the latent space of StyleGAN models (Gui et al., 2020).”
BackgroundMiotto, R. F., & Wolf, W. R. (2023) · Physics of Fluids · doi:10.1063/5.0144700 · Cited by 12
Wang, Y.-Z., Li, Y., Aubry, N., Hua, Y., Zhou, Z., Chen, Z., & Wu, W. (2023) · Physics of Fluids · doi:10.1063/5.0158049 · Cited by 13
Review of Deep Learning Approaches for Interleaved Photoacoustic and Ultrasound (PAUS) Imaging
Kim, M., Pelivanov, I., & O’Donnell, M. (2023) · IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control · doi:10.1109/tuffc.2023.3329119 · Cited by 15
“Generative adversarial networks (GANs) [89], [90] can output more plausible images using ingenious cost (loss) functions for optimization beyond standard metrics such as mse or mean absolute error (MAE).”
BackgroundGenerative Adversarial Network-Based Scheme for Diagnosing Faults in Cyber-Physical Power Systems
Hassani, H., Razavi‐Far, R., Saif, M., & Palade, V. (2021) · Sensors · doi:10.3390/s21155173 · Cited by 15
“The discriminator model, however, aims to discriminate the generated data examples by means of the generator from the true data examples [26].”
BackgroundJin, Y., Ma, J., Lin, Y., Cheng, J., & Sun, D. (2025) · Food Engineering Reviews · doi:10.1007/s12393-025-09418-5 · Cited by 11
Zielinski, C., Winker, M. A., Aggarwal, R., Ferris, L. E., Heinemann, M., Jose Florencio Lapeña, Jr., Pai, S. A., Ing, E., Citrome, L., Alam, M., et al. (2023) · Journal of Postgraduate Medical Institute · doi:10.54079/jpmi.37.3.3284 · Cited by 12
Alsafadi, F., & Wu, X. (2023) · Nuclear Engineering and Design · doi:10.1016/j.nucengdes.2023.112712 · Cited by 12
Improved Conditional Domain Adversarial Networks for Intelligent Transfer Fault Diagnosis
Qin, H., Pan, J., Li, J., & Huang, F. (2024) · Mathematics · doi:10.3390/math12030481 · Cited by 12
Zhang, Y., Zhou, P., & Ma, E. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3375410 · Cited by 13
“The GAN is considered to be a powerful generative model based on deep learning and has found applications across diverse domains [23].”
BackgroundA Category-Aware Curriculum Learning for Data-Free Knowledge Distillation
Li, X., Jiao, L., Sun, Q., Liu, F., Liu, X., Li, L., Chen, P., & Yang, S. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3395844 · Cited by 12
Equivalent Circuit-Guided GAN Sample Generation of Metasurface for Low-RCS Scanning Array
Liu, Z., Shao, W., Ding, X. F., Wang, B., Peng, L. F., & Chen, Z. N. (2024) · IEEE Transactions on Antennas and Propagation · doi:10.1109/tap.2024.3430078 · Cited by 11
“D ( x | y ) assesses the probability that x is the real geometry or it is generated by the generator with y , and G ( z | y ) generates a meta-atom pattern with the input composed of z and the desired response y [31].”
BackgroundDeep learning in disease vector image identification
Bai, S., Shi, L., & Yang, K. (2024) · Pest Management Science · doi:10.1002/ps.8473 · Cited by 13
Deep Learning for Automated Aircraft Surface Defect Detection
Bhatia, V., Arora, R., & Sidharth, S. (2024) · International Conference on Intelligent Computing and Emerging Communication Technologies (ICEC) · doi:10.1109/icec59683.2024.10837564 · Cited by 13
“GANs are not involved in direct detection of defects, but they can play a crucial role in data augmentation[23].”
Masoudifar, M., Mahsuli, M., & Taciroğlu, E. (2025) · Soil Dynamics and Earthquake Engineering · doi:10.1016/j.soildyn.2025.109306 · Cited by 11
Ye, J., He, J., Zhang, X., Lin, Y., Lin, H., He, C., & Li, W. (2025) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2025.3585358 · Cited by 22
“Despite these advancements, GAN-based models still face inherent challenges such as mode collapse, training instability, and low-quality synthesized images [38], [39], which limit their generalization ability in complex scenarios.”
Self-citationExploring the Advancements and Challenges of Deepfake Face-swap: A Survey
Bakar, S. A. R. B. S. A., Waseem, S., Omar, Z., & Bilalashfaqahmed (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21285-8 · Cited by 15
Double Generative Adversarial Networks for Conditional Independence Testing
Shi, C., Xu, T., Bergsma, W., & Li, L. (2020) · London School of Economics and Political Science Research Online (London School of Economics and Political Science) · doi:10.48550/arxiv.2006.02615 · Cited by 11
Adversarial training and ensemble learning for automatic code summarization
Zhou, Z., Yu, H., & Fan, G. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-05907-w · Cited by 11
“We borrow the idea of adversarial training [28], the most popular way to train generative models in computer vision [54], to train our models.”
BackgroundMethodThe P3 indexes the distance between perceived and target image
de la Torre‐Ortiz, C., Spapé, M., & Ruotsalo, T. (2023) · Psychophysiology · doi:10.1111/psyp.14225 · Cited by 14
English Emotional Voice Conversion Using StarGAN Model
Meftah, A. H., Alashban, A. A., Alotaibi, Y. A., & Selouani, S. (2023) · IEEE Access · doi:10.1109/access.2023.3292003 · Cited by 11
“Recently, Generative Adversarial Networks (GANs), including various versions such as Star-consistent Generative Adversarial Networks (StarGAN) and Cycle-GAN, among others, have been the most popular methods employed in EVC frameworks [5].”
MethodChen, Y., Yan, Y., Wang, X., & Zheng, Y. (2023) · Sensors · doi:10.3390/s23146531 · Cited by 13
“Then, we find the minimum value of the function to obtain the optimal parameter value of the generator [23,24].”
BackgroundOpen Set Classification of GAN-based Image Manipulations via a ViT-based Hybrid Architecture
Wang, J., Alamayreh, O., Tondi, B., & Barni, M. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00102 · Cited by 19
“Synthetic manipulation of face images has become ubiquitous and is being increasingly used in a wide variety of applications [15], thus posing a serious threat to public trust.”
BackgroundSUGAN: A Stable U-Net Based Generative Adversarial Network
Cheng, S., Wang, L., Zhang, M., Zeng, C., & Meng, Y. (2023) · Sensors · doi:10.3390/s23177338 · Cited by 12
“Between the two metrics, FID is considered a more reasonable and comprehensive measure, following the practice in the references of [6,42,50].”
BackgroundMethodHashemi, S. M., Hashemi, S. A., Botez, R. M., & Ghazi, G. (2023) · Applied Sciences · doi:10.3390/app13179503 · Cited by 11
Lin, S., Chen, W., Alqahtani, M. S., Elkamchouchi, D. H., Ge, Y., Lu, Y., Zhang, G., & Wang, M. (2023) · Environmental Research · doi:10.1016/j.envres.2023.117262 · Cited by 11
Human-Inspired Facial Sketch Synthesis with Dynamic Adaptation
Gao, F., Zhu, Y., Jiang, C., & Wang, N. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00665 · Cited by 15
“Our work is related to GANs-based FSS methods.”
MethodInfluentialNazir, A., Mir, R. N., & Qureshi, S. (2020) · International Journal of Intelligent Computing and Cybernetics · doi:10.1108/ijicc-04-2020-0038 · Cited by 13
A Novel Framework for Selection of GANs for an ApplicationPreprint
Motwani, T., & Parmar, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.08641 · Cited by 16
A Survey on Federated Learning PoisoningAttacks and DefensesPreprint
Liang, J., & Rong, W. (2022) · Research Square · doi:10.21203/rs.3.rs-1900743/v1 · Cited by 17
Wang, R., Zhao, Z., Sun, Y., Ni, Y., Ye, J., Zhang, M., & Cui, L. (2025) · Food Chemistry · doi:10.1016/j.foodchem.2025.146910 · Cited by 16
Self-citationApplication of Deep Learning Neural Networks in Computer-Aided Drug Discovery: A Review
Mathivanan, J. S., Dhayabaran, V. V., David, M. R., Nidhi, M. B. K., Prasath, K. M., & Suvaithenamudhan, S. (2024) · Current Bioinformatics · doi:10.2174/0115748936276510231123121404 · Cited by 11
Hu, B., Liu, J., Xu, Y., & Huo, T. (2024) · Shock and Vibration · doi:10.1155/2024/9071328 · Cited by 10
Leible, S., Gücük, G.-L., Simic, D., von Brackel-Schmidt, C., & Lewandowski, T. (2024) · HMD Praxis der Wirtschaftsinformatik · doi:10.1365/s40702-024-01050-x · Cited by 16
Performance Enhancement of Alzheimer's Disease Diagnosis Using Generative Adversarial Network
Ching, W. P., Abdullah, S. S., Shapiai, M. I., & Islam, A. K. M. M. (2024) · Journal of Advanced Research in Applied Sciences and Engineering Technology · doi:10.37934/araset.45.2.191201 · Cited by 10
Chen, M., Wang, K., Dohopolski, M. J., Morgan, H., Sher, D. J., & Wang, J. (2025) · Medical Physics · doi:10.1002/mp.17655 · Cited by 11
Defending against and generating adversarial examples together with generative adversarial networks
Wang, Y., Liao, X., Cui, W., & Yang, Y. (2025) · Scientific Reports · doi:10.1038/s41598-024-83444-x · Cited by 13
“Generative Adversarial Network (GAN) has become one of the most promising methods for unsupervised learning in complex distribution in recent years 22,23 .”
A Survey on Human Interaction Motion Generation
Sui, K., Ghosh, A., Hwang, I., Zhou, B., Wang, J., & Guo, C. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-025-02582-5 · Cited by 36
“This advancement has been driven by foundational generative models, including Variational Autoencoders (VAEs) [103], Generative Adversarial Networks (GANs) [66], Diffusion models [38, 252], Large Language Models (LLMs) [150], and Vision-Language Models (VLMs) [123].”
GANs and Artificial Facial Expressions in Synthetic Portraits
Rodrigo, P. R., Blanco, R. F., & Reverter, F. (2021) · Big Data and Cognitive Computing · doi:10.3390/bdcc5040063 · Cited by 10
Infrared-Visible Image Fusion Based on Semantic Guidance and Visual Perception
Chen, X., Teng, Z., Liu, Y., Lu, J., Bai, L., & Han, J. (2022) · Entropy · doi:10.3390/e24101327 · Cited by 11
“It has profound and wide applications in the field of image generation [13].”
BackgroundEfficient subsampling of realistic images from GANs conditional on a class or a continuous variable
Ding, X., Wang, Y., Wang, Z. J., & Welch, W. J. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.10.070 · Cited by 12
Multi-scale governance and data for sustainable development
Pastor-Escuredo, D., Gardeazabal, A., Koo, J., Imai, A., & Treleaven, P. C. (2022) · Frontiers in Big Data · doi:10.3389/fdata.2022.1025256 · Cited by 10
“, 2018) and Generative Adversarial Networks (GANs) (Liu and Tuzel, 2016; Metz et al., 2016; Mao et al., 2017; Wang et al., 2017; Creswell et al., 2018; Gui et al., 2021), which have provided the sufficient amount of indicators with a high temporal resolution and a narrow geographical resolution.”
BackgroundLearning With Asymmetric Kernels: Least Squares and Feature Interpretation
He, M., He, F., Ши, Л., Huang, X., & Suykens, J. A. K. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3257351 · Cited by 14
“KL divergence has been successfully used in many fields, e.g., VAE [37] and GAN [38], [39].”
MethodMao, X., Wan, H., Wen, H., Wu, F., Zheng, J., Qiang, Y., Guo, S., Wu, L., Hu, H., & Lin, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i4.25578 · Cited by 10
“On the other hand, the training of GAN is difficult and often unstable (Gui et al. 2021).”
BackgroundShip Detection in Low-Quality SAR Images via an Unsupervised Domain Adaption Method
Pu, X., Jia, H., Xin, Y., Wang, F., & Wang, H. (2023) · Remote Sensing · doi:10.3390/rs15133326 · Cited by 12
Evading Forensic Classifiers with Attribute-Conditioned Adversarial Faces
Shamshad, F., Srivatsan, K., & Nandakumar, K. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01580 · Cited by 15
“While these synthetic/fake faces have many positive applications in video games, make-up industry, and computer-aided designs [11], they can also be mis-used for malicious purposes causing serious security and ethical problems.”
Maize Leaf Compound Disease Recognition Based on Attention Mechanism
Dong, P., Li, K., Wang, M., Li, F., Guo, W. F., & Si, H. (2023) · Agriculture · doi:10.3390/agriculture14010074 · Cited by 10
Arora, S., Mittal, R., Shrivastava, A. K., & Bali, S. (2024) · International Journal of Quality & Reliability Management · doi:10.1108/ijqrm-12-2022-0373 · Cited by 12
Ang, J. L. Y., Tan, K. H., Yong, A. S. K., Tan, C. W. X., Kng, J. S. J., Tan, C. J. J., Soh, R. H. K., Tan, J. Y. H., & Liang, K. (2024) · Optica · doi:10.1364/optica.515501 · Cited by 11
Unsupervised and lightly supervised learning in particle physics
Bardhan, J., Mandal, T., Mitra, S., Neeraj, C., & Patra, M. (2024) · The European Physical Journal Special Topics · doi:10.1140/epjs/s11734-024-01235-x · Cited by 12
“For an illustration, let us consider the example given in Ref.”
Zhang, S., Ma, X., Nie, Z., Cheng, W., Xing, J., Zhang, L., Hong, J., Xu, Z., & Chen, X. (2024) · Measurement · doi:10.1016/j.measurement.2024.115811 · Cited by 10
The application of artificial intelligence in upper gastrointestinal cancers
Huang, X., Qin, M., Fang, M., Wang, Z., Hu, C., Zhao, T., Qin, Z., Zhu, H., Wu, L., Yu, G., et al. (2024) · Journal of the National Cancer Center · doi:10.1016/j.jncc.2024.12.006 · Cited by 16
“22 , 23”
A Marr's Three‐Level Analytical Framework for Neuromorphic Electronic Systems
Guo, Y., Zou, X., Hu, Y., Yang, Y., Wang, X., He, Y., Kong, R., Guo, Y., Li, G., Zhang, W., et al. (2021) · Advanced Intelligent Systems · doi:10.1002/aisy.202100054 · Cited by 16
Multiple agents’ spatiotemporal data generation based on recurrent regression dual discriminator GAN
Bao, P., Chen, Z., Wang, J., & Dai, D. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.10.048 · Cited by 11
Fractional SDE-Net: Generation of Time Series Data with Long-term Memory
Hayashi, K., & Nakagawa, K. (2022) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa54385.2022.10032351 · Cited by 22
“As to learning of population distribution, generative adversarial network (GAN) advocated in [2] is a basic approach in spite of the great success of GANs with images [3].”
BackgroundData Augmentation for Industrial Prognosis Using Generative Adversarial Networks
Ortego, P., Diez-Olivan, A., Ser, J. D., & Sierra, B. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-62365-4_11 · Cited by 10
Monte Carlo guided Diffusion for Bayesian linear inverse problems
Cardoso, G., Idrissi, Y. J. E., Corff, S. L., & Moulines, É. (2023) · International Conference on Learning Representations · doi:10.48550/arxiv.2308.07983 · Cited by 67
Losi, E., Manservigi, L., Spina, P. R., & Venturini, M. (2024) · Journal of Engineering for Gas Turbines and Power · doi:10.1115/1.4066360 · Cited by 10
Mansour, S., Jabra, S. B., & Zagrouba, E. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20258-z · Cited by 11
“Amongdeep-learningmodels widelyusedinwatermarkingtechniques,wecanmentiontheconvolutionalneuralnetwork (CNN)[73],therecurrentneuralnetwork(RNN)[74],thegenerativeadversarialnetwork (GAN)[75],andtheAutoencoder[76].”
A general image classification model for agricultural machinery trajectory mode recognition
Zhai, W., Xu, Z., Pan, J., Guo, Z., & Wu, C. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.109629 · Cited by 9
Peng, G., Liu, M., Chen, S., Tao, M., Li, Y., & Xing, M. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3502454 · Cited by 9
Zhan, Z., Zhong, C., Zheng, J., & Zhong, W. (2024) · Communications in computer and information science · doi:10.1007/978-981-96-0205-6_2 · Cited by 9
A High-Performance Memristive Circuit Design for DCGAN in Edge Computing
Guo, M. L., Sun, J., Dou, G., & Iu, H. H. (2025) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2025.3554750 · Cited by 12
“Generative Adversarial Networks (GAN) [23] have been widely used in various image-processing applications [24], [25].”
Cen, J., Si, W., Liu, X., Zhao, B., Huang, H., & Liu, J. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06535-w · Cited by 9
“Commonly used generative models include Generative Adversarial Network (GAN) and Variational Autoencoder (VAE) [13, 14].”
Machine Learning-Based High Entropy Alloys-Algorithms and Workflow: A Review
Cheng, H., Wang, C., Li, X.-D., Pan, L., Liang, C., & Liu, W. (2025) · Acta Metallurgica Sinica (English Letters) · doi:10.1007/s40195-025-01894-2 · Cited by 10
Omiyale, B. O., Ogedengbe, I. I., Odeyemi, J., Ogbeyemi, A., Olorunsogbon, F., & Zhang, W. C. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-16100-x · Cited by 10
Application of Artificial Intelligence in Predicting Coal Mine Disaster Risks: A Review
Lu, P., Liu, Y., Liang, Y., & Cui, D. (2025) · Sensors · doi:10.3390/s25216586 · Cited by 10
“As illustrated in Figure 3, GAN can generate synthetic samples that approximate the distribution of real data, thereby alleviating issues of limited datasets and class imbalance in disaster monitoring [43,44].”
The Level of Generative AI Use Among University Students and the Factors That Influence Its Use
Parikesit, B. A. B., & Mauritsius, T. (2025) · International Journal of Information and Education Technology · doi:10.18178/ijiet.2025.15.11.2452 · Cited by 9
“The network repeats the cycle of generating and discriminating content until the generator produces content that the discriminator cannot distinguish between real and synthetic [18].”
Liang, J., Zhou, Y., Ma, K., Jia, Y., Zhang, Y., Han, B., & Xiang, M. (2026) · Bioengineering · doi:10.3390/bioengineering13010084 · Cited by 9
Artificial neural networks for NAA: proof of concept on data analysed with k0-based software
Barradas, N. P., Farjallah, N., Vieira, A. S., & Blaauw, M. (2022) · Journal of Radioanalytical and Nuclear Chemistry · doi:10.1007/s10967-022-08568-8 · Cited by 9
“Generative models, capable of producing new data from a learned model, have made tremendous progress in recent years, since the initial proposal of Generative Adversarial Networks (GANs) [34].”
BackgroundGenerating Synthetic Data for Credit Card Fraud Detection Using GANs
Strelcenia, E., & Prakoonwit, S. (2022) · International Conference on Computers and Artificial Intelligence Technology (CAIT) · doi:10.1109/cait56099.2022.10072179 · Cited by 9
“The study by [8] is unique from the above studies as their study examined GAN in theoretical and mathematical approaches.”
ResultDon’t Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance
Liu, S., Tian, Y., Chen, T., & Shen, L. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01824-8 · Cited by 18
“Unbalanced GAN Training”
Deep learning in optics—a tutorial
Hadad, B., Froim, S., Yosef, E., Giryes, R., & Bahabad, A. (2023) · Journal of Optics · doi:10.1088/2040-8986/ad08dc · Cited by 13
“Therefore, some variations were suggested to improve stability and results [36, 37].”
BackgroundModeling Epidemics: Neural Network Based on Data and SIR-Model
Игоревна, К. О., Zyatkov, N., & Kabanikhin, S. I. (2023) · Computational Mathematics and Mathematical Physics · doi:10.1134/s096554252310007x · Cited by 9
“This can be done using deep learning meth-ods, such as autoencoders [2] or generative–adversarial networks [3], which can reveal hidden patterns in data and create mathematical models based on these patterns.”
BackgroundAlexiou, M. S., & Mertoguno, J. S. (2023) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai59109.2023.00047 · Cited by 12
“Prior surveys have extensively covered important topics of GANs [80, 81, 82, 83], offering valuable insights into various aspects of GAN architecture, training strategies, and dataset usage.”
BackgroundTraining of a deep learning based digital subtraction angiography method using synthetic data
Duan, L., Eulig, E., Knaup, M., Adamus, R., Lell, M., & Kachelrieß, M. (2024) · Medical Physics · doi:10.1002/mp.16973 · Cited by 9
Emerging Directions in Bayesian Computation
Winter, S., Campbell, T., Lin, L., Srivastava, S., & Dunson, D. B. (2024) · Statistical Science · doi:10.1214/23-sts919 · Cited by 25
Kim, J.-Y., & Choi, G. (2024) · Asia-pacific Journal of Convergent Research Interchange · doi:10.47116/apjcri.2024.02.09 · Cited by 12
Enhancing GAN Performance Through Neural Architecture Search and Tensor Decomposition
Pulakurthi, P. R., Mozaffari, M., Dianat, S. A., Rabbani, M., Heard, J. R., & Rao, R. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446488 · Cited by 9
“They have been successfully applied in the field of computer vision [1] and deep learning [2] to various tasks such as image-to-image translation [3], text-to-image synthesis [4], human pose synthesis [5], image generation [6], and speech synthesis [7].”
BackgroundEdgeGAN: Enhancing Sleep Quality Monitoring in Medical IoT Through Generative AI at the Edge
Peng, K., He, H., Liu, J., Li, T., Hou, S., & Qiao, S. (2024) · IEEE Internet of Things Magazine · doi:10.1109/iotm.001.2300276 · Cited by 9
Purwanto, A. J., Kusrini, K., Utami, E., & Agustriawan, D. (2024) · IEEE International Conference on Artificial Intelligence and Mechatronics Systems (AIMS) · doi:10.1109/aims61812.2024.10513308 · Cited by 9
“In particular, generative adversarial networks (GANs) with a cyclic formulation, which are trained on unpaired pictures and stylized images, are used to increase style transmission [5].”
BackgroundAnwar, A., Khalifa, Y., Lucatorto, E., Coyle, J. L., & Sejdić, E. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102921 · Cited by 9
Variational image registration with learned prior using multi-stage VAEs
Hua, Y., Xu, K., & Yang, X. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108785 · Cited by 13
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.