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 901–1,000 of 1,002
Transformation in Human–Computer Interaction: The AI-Enabled NLP
Sharma, H., Anubha, A., & Narang, D. (2025) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-83549-852-120251003 · Cited by 2
Kostenko, O. V., Vira, T., Halyna, U., Ulianov, O., Larysa, H., Orzikh, Y., Sibilla, B., Alla, K., Oleksandr, B., Nataliya, B., et al. (2025) · doi:10.69635/978-1-0690482-4-0 · Cited by 5
B2BGAN: A Backbone-to-Branches GAN-Based Oversampling Approach for Class-Imbalanced Tabular Data
Wang, X., Wang, C., Wang, M., Liu, J., & Guan, X. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3593637 · Cited by 3
“Recentyearshavewitnessedgreatsuccessforgenerative adversarialnetworks(GANs)insimulatingreal-worlddata distributions[13].”
Wu, Z. X., Zhang, Q., Miao, D., Zhao, X., Bao, G., Hu, L., Yi, K., & Zhou, Y. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103578 · Cited by 2
FetalFlex: Anatomy-guided diffusion model for flexible control on fetal ultrasound image synthesis
Duan, Y., Tan, T., Zhu, Z., Huang, Y., Zhang, Y., Gao, R. T., Pang, P. C., Gao, X., Tao, G., Xiang, C., et al. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103725 · Cited by 12
“However, despite being easy to implement, their e ff ectiveness in control-lability and enhancing dataset diversity remains limited (Frid-Adar et al., 2018a; Gui et al., 2021).”
3D porous media image synthesis using conditional GAN
Dheyauldeen, A., Wang, Y. D., Tang, K., Armstrong, R. T., & Mostaghimi, P. (2025) · Computers & Geosciences · doi:10.1016/j.cageo.2025.106016 · Cited by 2
Generative Adversarial Networks (GAN) based Person Re-Identification : A Review
Sharma, I., Kapoor, P., & Vaidya, P. (2025) · International Conference on Electronics, AI and Computing (EAIC) · doi:10.1109/eaic66483.2025.11101528 · Cited by 2
“The following equation represents the optimization problem of a Generative Adversarial Network [15].”
YOLO-Based Third-Rail Defect Detection With BGAN-Augmented Training
Chung, M., Lin, C.-W., Gao, C.-Y., Ma, Y., Chen, P.-C., Lin, J.-W., & Lin, C.-C. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3598914 · Cited by 2
“The goal of the overall model is shown in the following equation [33]: where D ( x ) represents the prediction value of the discriminator D for real data x .”
InfluentialJia, S., Liang, S., Mo, Z., Liu, C., Wang, H., & Chen, C. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129406 · Cited by 3
Exploiting the connections between images and deep feature vectors in model inversion attacks
Zhang, Z., & Huang, J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131457 · Cited by 2
Huertas-García, R., Sáez‐Ortuño, L., Forgas‐Coll, S., & Sánchez, J. (2025) · Journal of Innovation & Knowledge · doi:10.1016/j.jik.2025.100828 · Cited by 3
Wu, X., Rezki, Z., Balusu, B., Zhou, J., & Bai, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130096 · Cited by 7
Zuo, J., Yao, Y., & Zhang, Y. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3624395 · Cited by 2
“To improve robustness against unexpected situations and anomalous data, we incorporate adversarial learning [40], [41], which allows ASTCIN to generate and learn from perturbation scenarios alongside normal tra ffi c conditions.”
A Novel GAN-Based Technique Towards Smarter Seismic Inversion
Mohebian, R., & Olya, B. A. M. (2025) · Abu Dhabi International Petroleum Exhibition & Conference (ADIPEC) · doi:10.2118/229776-ms · Cited by 2
Underwater dam image enhancement based on CNN-transformer fusion
Yang, Z., Yuan, C., Li, L., Ding, P., Zou, J., Wang, K., & Zhu, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-23746-w · Cited by 2
Zhao, Z. (2025) · Intelligent Decision Technologies · doi:10.1177/18724981251394990 · Cited by 2
“A Generative Adversarial Network (GAN) consists of two neural networks 12,13 that compete with each other.”
He, R., Liu, X., Wang, Y., Tian, Z., Zuo, M. J., & Ye, Z. (2025) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2025.111979 · Cited by 2
Neural Network Architectures for Enhancing Data Center Intelligence through Deep Learning
Castillo, A. C. (2025) · International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) · doi:10.1109/ismsit67332.2025.11268124 · Cited by 2
“It is worth mentioning that the GIA uses a sub-branch called Deep Learning, which translates into content modeling based on specific scales that occur in texts, graphics, audio, and video [3,4].”
Bio-Inspired Generative Network with Knowledge Integration
Batbaatar, E., & Ryu, K. H. (2025) · Applied Sciences · doi:10.3390/app152412918 · Cited by 2
Zhang, Z. F., Liang, D., Tang, G., Hua, Y., Dong, B., & Liang, Z. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113474 · Cited by 4
A parametric maize leaf model quantifying morphology and geometry via 3D triangle mesh
Xiang, Z., & Ge, Y. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.111218 · Cited by 2
Wu, C.-L., Chen, Y.-Y., Chou, P.-Y., & Wang, C.-Y. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3653576 · Cited by 3
“Generative adversarial network (GAN) is a modern generative model for learning the distribution of interest with deep structures, and GAN achieved immense success in various areas, such as computer vision, signal processing, and natural language processing [6], [7].”
Efficient incomplete multi-view tensor clustering through predefined anchor learning
Han, Z., & Xu, Y. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.114660 · Cited by 2
Generative AI in different imaging modalities for disease diagnosis: A review
Ali, T. M., Zia‐ur‐Rehman, Hijji, M., Ayaz, M., Albelwi, S. A., & Ijaz, M. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131162 · Cited by 4
Wasserstein GAN-based estimation for conditional distribution function with current status data
Su, W., Liu, C., Yin, G., & Huang, J. (2026) · Lifetime Data Analysis · doi:10.1007/s10985-026-09691-4 · Cited by 2
Intelligent terahertz data analysis in agriculture: A systematic review of AI-driven approaches
Sun, Z., Luo, X., Xu, W., Wang, C., & Ying, Y. (2026) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2026.118748 · Cited by 3
Self-citationThree-band SWIR imaging for Pix2Pix-based colorization
Chen, Q., Liu, X., Du, L., BO, S., Sun, X., & SHEN, Z. (2026) · Applied Optics · doi:10.1364/ao.590489 · Cited by 3
Deep Learning‐Based Data Hiding Techniques for Secure Communication: A Comprehensive Review
Awasthi, D., Tiwari, A., Khare, P., & Srivastava, V. K. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70706 · Cited by 3
“Due to its efficacy in creating fresh image samples and utility in preventing domain shift, the adversarial training system has drawn interest from both academia and industry [56].”
Cross-Modal Graph Attention for Bridge SHM Data Imputation
Xiong, J., Hu, L., Meng, X., An, X., & Xie, Y. (2026) · Sensors · doi:10.3390/s26113339 · Cited by 2
“As an emerging data-driven paradigm, Generative Adversarial Networks (GANs), since their introduction by Goodfellow [29], have combined the strengths of generative and discriminative models and undergone a series of improvements [30,31].”
From simulator to surrogate: GANs for spatiotemporal modeling of subsurface flow in porous media
Tariq, Z., Feng, Z., Yan, B., & Hoteit, H. (2026) · Computational Geosciences · doi:10.1007/s10596-026-10440-7 · Cited by 2
Small, imbalanced, and noisy datasets in healthcare research: A systematic review
Ramos, J., Pais-Vieira, M., & Brás, S. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115472 · Cited by 4
Hu, J., Wu, W., Zhou, P., Dai, Y., & Wang, H. (2026) · Energy and Buildings · doi:10.1016/j.enbuild.2026.118152 · Cited by 1
Deep Learning for Digital Pathology in Limited Data Scenarios
Stacke, K. (2022) · Linköping studies in science and technology. Dissertations · doi:10.3384/9789179294748 · Cited by 2
A Framework Pipeline to Address Imbalanced Class Distribution Problem in Real-world Datasets
Chinta, U., & Atyabi, A. (2023) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc57344.2023.10099163 · Cited by 3
“Sungho et al. [6] introduced a method based on Generative Adversarial Network (GAN) [11], which takes a random noise input and generates a new dataset and concluded that their proposed method would increase imbalanced classification by 2.73%, 3.13%, 5.19%, 6.78%, and 3.31% on the MNIST, EMNIST,…”
MethodInfluentialPu, X., Jia, H., & Xu, F. (2023) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss52108.2023.10282746 · Cited by 3
Anti-Jamming Method of Near-Field Underwater Acoustic Detection Based on WGAN
Jingbo, Z., Jiang, Z., Li, D., & Wang, H. (2023) · IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) · doi:10.1109/icspcc59353.2023.10400212 · Cited by 2
“GANs often encounter issues like gradient vanishing and mode collapse during application [12].”
BackgroundA Perturbed Convolutional Layer and Gradient Normalization based Generative Adversarial Network
Wang, Z., & Cai, J. (2024) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice61279.2024.10498349 · Cited by 2
“One notable approach is the Wasserstein Generative Adversarial Network (WGAN) [8], which addresses GAN stability concerns by employing the Wasserstein (or Earth Mover’s) distance as its training loss function.”
MethodJeczmionek, E., & Kowalski, P. A. (2023) · International Journal of Applied Mathematics and Computer Science · doi:10.34768/amcs-2023-0047 · Cited by 4
“In recent years, exploratory data analysis has undergone significant developments in both theoretical (Gui et al ., 2021) and practical (Saura, 2021) aspects.”
MethodLu, J., Gu, R., Liao, W., Zhang, S., Yu, H., Zhang, S., & Wang, G. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128115 · Cited by 3
Flakyrank: Predicting Flaky Tests Using Augmented Learning to Rank
Wang, J., Yan, L., Li, M., Ren, G., Xie, H., Jin, S., Li, J., & Hu, J. (2024) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner60148.2024.00095 · Cited by 4
“Generative Adversarial Networks (GANs) [29], [33] are a type of deep learning model used for data generation.”
BackgroundLiu, J. (2024) · International Conference on Data Science and Information System (ICDSIS) · doi:10.1109/icdsis61070.2024.10594192 · Cited by 2
“…convolution and pooling operations are adopted to take the hierarchical correspondence between x and y. 3) Teacher Forcing: Although generative adversarial networks have been widely applied in various fields such as computer vision, the instability issues they face have always been discussed [20].”
BackgroundLearning to Imitate Spatial Organization in Multi-robot Systems
Agunloye, A. O., Ramchurn, S. D., & Soorati, M. D. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801662 · Cited by 3
“We transform D into informed multi-agent interactions before recovering policies that accurately reproduce expert behaviors using multi-agent GAIL (MA-GAIL) [28].”
Spectrum Anomaly Detection Method Fusing Time-Frequency Attention
Zhang, R., Ji, H., Li, W., Shang, Z., & Zhang, T. (2024) · International Symposium on Computer Engineering and Intelligent Communications (ISCEIC) · doi:10.1109/isceic63613.2024.10810202 · Cited by 2
Generative adversarial network for 3D super-resolution in fringe projection profilometry
Wan, C., Gai, S., & Da, F. (2025) · Optics & Laser Technology · doi:10.1016/j.optlastec.2024.112324 · Cited by 2
GAN Stabilization Under Practical Training Assumptions
DeOliveira, J., Gerych, W., & Rundensteiner, E. A. (2024) · BigData Congress [Services Society] · doi:10.1109/bigdata62323.2024.10825612 · Cited by 2
Robust Metadata Forensics to Improve Detection and Analysis of Deepfake Images
Royan, N., Safitri, C., & Sen, T. W. (2024) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti64779.2024.10963532 · Cited by 2
“For hyperparameter optimization, we used grid search to increase the accuracy of the models by finding the best parameter combination for each algorithm [24].”
scSTD: A Swin Transformer-Based Diffusion Model for Recovering scRNA-Seq Data
Li, Y., Liu, F., Zhou, J., Shi, F., & Yu, Z. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3570265 · Cited by 3
“While GANs have also been applied for cell clustering with notable success [38], their adversarial training often suffers from instability and mode collapse [39], leading to low sample diversity and poor coverage of rare cell subtypes.”
Lin, Y., Cai, Y., Chen, H., Cai, Y., Lin, Z., Cai, H., & Ni, H. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/aded2a · Cited by 2
Syed, T. H., Kulkarni, A. R., & Niamat, M. Y. (2025) · IEEE International Conference on Secure IoT, Assured and Trusted Computing (SATC) · doi:10.1109/satc65530.2025.11136906 · Cited by 2
“The discriminator loss, defined as a binary cross-entropy function, penalizes the discriminator when it fails to correctly classify real data versus synthetic data [28].”
Saturated Terminology Extraction and Analysis in Use
Kosa, V., & Ermolayev, V. (2022) · Cognitive science and technology · doi:10.1007/978-981-16-8630-6_6 · Cited by 2
Image Generation from a Hyper Scene Graph with Trinomial Hyperedges
Miyake, R., Matsukawa, T., & Suzuki, E. (2023) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0011699300003417 · Cited by 3
“We confirmed that simply increasing the resolution of the generated images does not work well due to the mode collapse (Gui et al., 2021), which is a phenomenon that the generated images are all similar to each other due to the training failure.”
Effect of Convulsion Layers and Hyper-parameters on the Behavior of Adversarial Neural Networks
Sabiri, B., Asri, B. E., & Rhanoui, M. (2023) · Lecture notes in business information processing · doi:10.1007/978-3-031-39386-0_11 · Cited by 2
Li, W., Tian, L., Sun, Z., & Li, X. (2023) · International Conference on Computing and Artificial Intelligence (ICCAI) · doi:10.1145/3594315.3594652 · Cited by 2
“To overcome the above challenges, we propose a layer mask blending-based generative adversarial network (LMBGAN), which combines adaptive discriminator augmentation [6] and nonsaturating logistic loss [7] to optimize the training process, aiming to generate more realistic and diverse surface defect samples.”
MethodSelf-citationHairstyle transfer via manipulating decoupled latent codes of StyleGAN2
Shao, M., Liu, F., Guo, Z., & Qiao, Y. (2023) · Computers & Graphics · doi:10.1016/j.cag.2023.09.003 · Cited by 3
Using Artificial Intelligence to Generate Synthetic Health Data
Girosi, F., Katragadda, S. P., Steier, J., & Vardavas, R. (2023) · RAND Corporation eBooks · doi:10.7249/wra2892-1 · Cited by 2
Shiga, M., & Watanabe, S. (2023) · The Materials Research Society series · doi:10.1007/978-981-99-5235-9_12 · Cited by 2
Collaborative Interactive Evolution of Art in the Latent Space of Deep Generative Models
Hall, O., & Yaman, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56992-0_13 · Cited by 4
“Therefore, many extensions and variants have been developed since then ([17], for an overview).”
BackgroundMethodEnhancing visual communication through representation learning
Wei, Y., Lee, C.-W., Han, S., & Kim, A. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1368733 · Cited by 2
Aligning the domains in cross domain model inversion attack
Zhang, Z., & Huang, J. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106490 · Cited by 4
Cloud-driven network security: A survey of methods, challenges, and innovations
Stefanidou, M., Maraslidis, G. S., Antoniadis, I. I., & Fragulis, G. F. (2024) · AIP conference proceedings · doi:10.1063/5.0234978 · Cited by 5
Wang, P., Ma, H., Liu, T., Liu, C., Li, D., & Ta, D. (2025) · Chinese Physics B · doi:10.1088/1674-1056/adb390 · Cited by 2
Rafner, J. F. (2025) · Oxford University Press eBooks · doi:10.1093/oxfordhb/9780197698181.013.0043 · Cited by 4
Advances in incremental learning research
Hao, F., Qian, F., Jiahang, T., Zhao, H., Zhang, C., Xin, D., & Qian, H. (2025) · Journal of Image and Graphics · doi:10.11834/jig.240790 · Cited by 2
Adversarial attacks to image classification systems using evolutionary algorithms
Nesmachnow, S., & Toutouh, J. (2025) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3712256.3726429 · Cited by 2
“GANs have been applied in many scientific and commercial fields, especially for generating synthetic images and videos [13].”
Darwich, M., & Bayoumi, M. (2025) · Cluster Computing · doi:10.1007/s10586-025-05538-z · Cited by 4
Pertsev, Y., & Korotka, L. (2025) · Transactions of Kremenchuk Mykhailo Ostrohradskyi National University · doi:10.32782/1995-0519.2025.4.26 · Cited by 4
Federated Quantum Generative Adversarial Network for Intrusion Detection
Cirillo, F., & Esposito, C. (2025) · IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW) · doi:10.1109/icdcsw63273.2025.00018 · Cited by 2
“A significant advancement in ML is the application of Generative Adversarial Networks (GANs) [4].”
Generative Adversarial Networks (GANs) for spatial upward fluxes radiation estimation
Eltahan, M., Daoud, N., & Moharm, K. (2021) · International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT) · doi:10.1109/icaect49130.2021.9392477 · Cited by 2
Cohen, A., & Derevyanko, S. (2021) · IEEE International Conference on Microwaves, Communications, Antennas and Electronic Systems (COMCAS) · doi:10.1109/comcas52219.2021.9629004 · Cited by 2
Siamese Generative Adversarial Predicting Network for Extremely Sparse Data in Recommendation System
Wang, Q., Zhang, R., Ma, K., Chen, B., Chen, J., & Shi, X. (2021) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom52081.2021.00170 · Cited by 2
Portraits Editing using StyleGANs & Transfer Learning
Rohilla, R., Bansal, H., Kediyal, G., & Dhamija, A. (2022) · International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc53470.2022.9754080 · Cited by 2
Generation of Synthetic Data: A Generative Adversarial Networks Approach
Ferreira, A. F., Magalhães, R. J. D. S., & Alves, V. (2022) · Advances in medical technologies and clinical practice book series · doi:10.4018/978-1-7998-9172-7.ch010 · Cited by 2
Oh, J.-H., Skiba, A. W., Hammack, S. D., Mitsingas, C. M., Carter, C. D., & Lee, T. (2022) · Energy and AI · doi:10.1016/j.egyai.2022.100207 · Cited by 2
Optimized Quantum Generative Adversarial Networks for Distribution Loading
Agliardi, G., & Prati, E. (2022) · IEEE International Conference on Quantum Computing and Engineering (QCE) · doi:10.1109/qce53715.2022.00132 · Cited by 5
“One of the most relevant classes of quantum machine learning algorithms consists of quantum generative adversarial networks (qGANs) [8], [9], [10], the quantum counterpart of GANs [11], [12].”
BackgroundFundamentals and Challenges of Generative Adversarial Networks for Image-based Applications
de Souza, V. L. T., Marques, B. A. D., & Gois, J. P. (2022) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi55357.2022.9991776 · Cited by 3
“However, generating images from different classes with a single network is still a challenge [3], [12].”
BackgroundMethodInfluentialCosine Similarity Based Representation Learning for Adversarial Imitation Learning
Zhang, X., Liu, Q., & Zhang, L. (2023) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53992.2023.10394257 · Cited by 2
“Recently, there have been numerous interesting works on IL. Ho & Ermon [6] propose Generative Adversarial Imitation Learning (GAIL), which shows a novel way to IRL by the Generative Adversarial Net (GAN) [7], [8].”
BackgroundThe investigation of performance improvement based on original GANs model
Zhang, H. (2024) · Applied and Computational Engineering · doi:10.54254/2755-2721/54/20241104 · Cited by 2
Multi-penalty Functions GANs via Multi-task Learning
Chen, H., He, H., & Chen, F. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-78609-0_2 · Cited by 2
Yang, Y., & Xu, S. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/6334802 · Cited by 2
“*e Discriminator tries to reduce the cost function for both natural and artificial samples, while Generator tries to increase the Discriminator cost function for the synthetic samples it produces.”
BackgroundMethodInfluentialRetractedScope of generative adversarial networks (GANs) in image processing
Kumari, S., & Aggarwal, K. (2022) · International Journal of Health Sciences · doi:10.53730/ijhs.v6ns6.9664 · Cited by 2
Robust Rule Based Neural Network Using Arithmetic Fuzzy Inference System
Dombi, J. D., & Hussain, A. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-16072-1_2 · Cited by 2
Training of Offline Handwritten Text Recognisers Using Computer-Generated TextPreprint
Ehiorobo, E. E., Koleoso, R. A., & Uwadia, C. O. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4055077 · Cited by 2
A Binded VAE for Inorganic Material GenerationPreprint
Oubari, F., de Mathelin, A., Décatoire, R., & Mougeot, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.09570 · Cited by 4
“Moreover, GANs and VAEs require their generations to be differentiable and thus fail to generate discrete compounds [5].”
BackgroundEnhanced Balanced-Generative Adversarial Networks to Predict Pedestrian Injury TypesPreprint
Somvanshi, S., Antariksa, G., & Das, S. (2024) · Research Square · doi:10.21203/rs.3.rs-4530893/v1 · Cited by 2
Castillo, L. R., Rafner, J. F., Nockur, L., & Buttlar, B. (2024) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/w6cj8 · Cited by 4
Natural Language Processing in Generative Adversarial Network
Dhivya, P., Karthikeyan, A., Pradeep, S., & Umamaheswari, H. (2025) · Wiley eBooks · doi:10.1002/9781394209835.ch4 · Cited by 2
Digital Economy Risk Prevention and Control System with Generative Adversarial Networks
Li, Z. (2023) · International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE) · doi:10.1109/aikiie60097.2023.10389914 · Cited by 1
“The organization and collaboration are not yet perfect, and an effective mechanism for information sharing and cooperation is not established, resulting in the isolation of risk information and the lack of coordination of prevention and control measures [18-19].”
BackgroundTransCycle: A Data Augmentation Method for 3D Human Pose Estimation
Zhang, B., Xu, R., & Cui, P. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447604 · Cited by 1
“Generative Adversarial Networks (GANs) [10] become a powerful tool in the field of computer vision, offering impressive capabilities in image generation, enhancement, and reconstruction.”
BackgroundHYDROSAFE: A Hybrid Deterministic-Probabilistic Model for Synthetic Appliance Profiles Generation
Jaradat, A., Alarbi, M., Haque, A., & Lutfiyya, H. L. (2024) · Sensors · doi:10.3390/s24175619 · Cited by 1
“Generative Adversarial Networks (GANs) [32] are rapidly evolving in many disciplines, including synthetic PCDs generation.”
BackgroundKemmou, A., Makrani, A. E., ELAZAMI, I., Lehlou, F., & Aabidi, M. H. (2024) · International Conference on Wireless Networks and Mobile Communications (WINCOM) · doi:10.1109/wincom62286.2024.10657959 · Cited by 2
“Concurrently, Generative Adversarial Networks (GANs) have emerged as powerful tools for image reconstruction tasks, although their application in FER, particularly in occlusion reconstruction, remains relatively unexplored [12-15].”
BackgroundDesign and Evaluation of Generative Adversarial Network for Automated Image Colorization System
Vidyalakshmi, R., Kathirvel, N., Gayathri, N., Bhuvaneshvari, K., Aarthi, M. S., & Sivaramkrishnan, M. (2024) · International Conference on Smart Electronics and Communication (ICOSEC) · doi:10.1109/icosec61587.2024.10722301 · Cited by 1
“A synopsis of their architecture and undertakings is provided below: The GAN training process involves optimizing the following objectives [14]: a. Generator Objective: The GN aims to generate colorized images that can deceive the discriminator.”
MethodFeng, K., Xin, S., Zhang, P., Yang, J., Fan, C., & Chen, C. (2024) · International Journal of Low-Carbon Technologies · doi:10.1093/ijlct/ctae251 · Cited by 1
Qin, R., Chen, N., & Gan, S. (2025) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001425550055 · Cited by 1
Sparse-to-Dense Body Surface Potential Mapping using A Structural Similarity-Enhanced Attention GAN
Mukherjee, A., Pratiher, S., Mazumder, O., & Sinha, A. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10887965 · Cited by 1
Enhancing Intrusion Detection Systems with representation methods: A comparative study
Meyer, B. H., Pozo, A., Nogueira, M., & Zola, W. M. N. (2025) · doi:10.1109/cisdb64969.2025.11010407 · Cited by 1
“Generative Adversarial Networks (GANs) involve two neural networks — the generator and the discriminator — in an adversarial process, enabling the generation of realistic data for anomaly detection [9].”
Design Method of Aging Service Robot Based on AIGC Incorporating TRIZ Theory
Yang, Y., Wu, L., & Zhao, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-93508-4_25 · Cited by 1
Generative Adversarial Networks in Histological Image Segmentation: A Systematic Literature Review
Cruz, Y. L. K. F., Silva, A. F. M., Santana, E. É. C., & Costa, D. G. (2025) · Applied Sciences · doi:10.3390/app15147802 · Cited by 1
DucDiff: Dual-Consistent Diffusion for Uncertainty-Aware Information Diffusion Prediction
Zhong, T., Ye, W., Li, S., Liu, Y., Cheng, Z., Zhou, F., & Chen, X. (2025) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2025.3598713 · Cited by 1
Enhancing Corrugation Detection via GAN-Based Data Augmentation
Chung, M., Lin, C.-W., Ma, Y., Chen, P.-C., Lin, J.-W., Lin, C.-C., & Gao, C.-Y. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3600280 · Cited by 1
“The loss function in GAN is defined as shown in the following equation [30]: where D ( x ) is the decision function for the real data x .”
Chai, D., Fang, Z., & Wu, F. (2025) · Regional Studies in Marine Science · doi:10.1016/j.rsma.2025.104450 · Cited by 2
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.