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
Items 201–332 of 332
Unsupervised Learning of Disentangled Representations from Video
Denton, E., & Birodkar, V. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.10915 · Cited by 205 · cited 2×
“Field Subfield Method Super-resolution SRGAN [63], ESRGAN [64], Cycle-in-Cycle GANs [65], SRDGAN [66], TGAN [67] DR-GAN [68], TP-GAN [69], PG2 [70], PSGAN [71], Image synthesis and manipulation APDrawingGAN [72], IGAN [73], Image processing and computer vision introspective adversarial networks [74], GauGAN [75] Textu…”
BackgroundMode Regularized Generative Adversarial Networks
Che, T., Li, Y., Jacob, A. P., Bengio, Y., & Li, W. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.02136 · Cited by 204 · cited 10×
“[26] introduce several methods of regularizing the objective, which can stabilize the training of GAN models.”
BackgroundMethodInfluentialFeedback GAN for DNA optimizes protein functions
Gupta, A., & Zou, J. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0017-4 · Cited by 203
A survey of image synthesis and editing with generative adversarial networks
Wu, X., Xu, K., & Hall, P. (2017) · Tsinghua Science and Technology · doi:10.23919/tst.2017.8195348 · Cited by 200 · cited 1×
“1) GANs for specific applications: There are surveys of using GANs for specific applications such as image synthesis and editing [5], audio enhancement and synthesis [6].”
BackgroundGP-GAN: Towards Realistic High-Resolution Image Blending
Wu, H., Zheng, S., Zhang, J., & Huang, K. (2019) · Proceedings of the 27th ACM International Conference on Multimedia · doi:10.1145/3343031.3350944 · Cited by 200 · cited 1×
“GANs have been utilized in other image processing and computer vision tasks [354]–[357] such as object transfiguration [358], [359], semantic segmentation [360], visual saliency prediction [361], object tracking [362], [363], image dehazing [364]–[366], natural image matting [367], image inpainting [368], [369], image…”
MethodLearning Texture Manifolds with the Periodic Spatial GANPreprint
Bergmann, U., Jetchev, N., & Vollgraf, R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.06566 · Cited by 200 · cited 2×
“Field Subfield Method Super-resolution SRGAN [63], ESRGAN [64], Cycle-in-Cycle GANs [65], SRDGAN [66], TGAN [67] DR-GAN [68], TP-GAN [69], PG2 [70], PSGAN [71], Image synthesis and manipulation APDrawingGAN [72], IGAN [73], Image processing and computer vision introspective adversarial networks [74], GauGAN [75] Textu…”
BackgroundGenerating Steganographic Images via Adversarial Training
Hayes, J., & Danezis, G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.00371 · Cited by 194 · cited 1×
“GANs have been widely used in many other areas such as malware detection [434], chess game playing [435], steganography [436]–[439], privacy-preserving [440]–[442], social robot [443], and network pruning [444], [445].”
MethodSCAN: Structure Correcting Adversarial Network for Organ Segmentation in Chest X-Rays
Dai, W., Dong, N., Wang, Z., Liang, X., Zhang, H., & Xing, E. P. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-00889-5_30 · Cited by 193 · cited 1×
“cal fields such as for generating and designing DNA [296], [297], drug discovery [298], generating multi-label discrete patient records [299], medical image processing [300], [301], [302], [303], [304], [305], [306], [307], and doctor recommen-”
BackgroundMGAN: Training Generative Adversarial Nets with Multiple Generators
Hoang, Q., Nguyen, T. D., Le, T., & Phung, D. (2018) · Figshare · Cited by 190
Banach Wasserstein GANPreprint
Adler, J., & Lunz, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.06621 · Cited by 189 · cited 1×
“Other papers related to WGAN can be found in [185], [186], [187],”
BackgroundZhao, J., Li, J., Cheng, Y., Sim, T., Yan, S., & Feng, J. (2018) · Proceedings of the 26th ACM international conference on Multimedia · doi:10.1145/3240508.3240509 · Cited by 187
Hilbert space embeddings and metrics on probability measures
Sriperumbudur, B. K., Gretton, A., Fukumizu, K., Schölkopf, B., & Lanckriet, G. R. G. (2009) · arXiv (Cornell University) · doi:10.48550/arxiv.0907.5309 · Cited by 183 · cited 5×
“Spectral normalization is capable of being generalized to any type of GANs’ variants while RGANs is able to be generalized to any IPM-based GANs.”
BackgroundInfluentialAlphaGAN: Generative adversarial networks for natural image mattingPreprint
Lutz, S., Amplianitis, K., & Smolić, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.10088 · Cited by 183 · cited 1×
“GANs have been utilized in other image processing and computer vision tasks [354]–[357] such as object transfiguration [358], [359], semantic segmentation [360], visual saliency prediction [361], object tracking [362], [363], image dehazing [364]–[366], natural image matting [367], image inpainting [368], [369], image…”
MethodLearning to Protect Communications with Adversarial Neural Cryptography
Abadi, M., & Andersen, D. G. (2016) · arXiv · doi:10.48550/arxiv.1610.06918 · Cited by 182 · cited 1×
“GANs have been widely used in many other areas such as malware detection [434], chess game playing [435], steganography [436]–[439], privacy-preserving [440]–[442], social robot [443], and network pruning [444], [445].”
MethodGeneralization and Equilibrium in Generative Adversarial Nets (GANs)
Arora, S., Ge, R., Liang, Y., Ma, T., & Zhang, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.00573 · Cited by 182 · cited 2×
“[301] show that training of GAN may not have good generalization properties; e.”
BackgroundLearning What and Where to Draw
Reed, S., Akata, Z., Mohan, S., Tenka, S., Schiele, B., & Lee, H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.02454 · Cited by 176 · cited 1×
“Based on cGANs, we can generate samples conditioning on class labels [30], [136], text [34], [137], [138], bounding box and keypoints [139].”
MethodLR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation
Yang, J., Kannan, A., Batra, D., & Parikh, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.01560 · Cited by 176 · cited 1×
“[345] proposed layered recursive GANs (LR-GAN) for image generation.”
BackgroundDeforming Autoencoders: Unsupervised Disentangling of Shape and Appearance
Shu, Z., Sahasrabudhe, M., Alp Güler, R., Samaras, D., Paragios, N., & Kokkinos, I. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01249-6_40 · Cited by 175
Santana, E., & Hotz, G. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.01230 · Cited by 174 · cited 1×
“MoCoGan [86] is proposed to decompose motion and content for video generation [348]–[350].”
BackgroundAPDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs
Yi, R., Liu, Y.-J., Lai, Y.-K., & Rosin, P. L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01100 · Cited by 172 · cited 1×
“Portrait Related: APDrawingGAN [60] was proposed to generate artistic portrait drawings from face photos with”
BackgroundSeGAN: Segmenting and Generating the Invisible
Ehsani, K., Mottaghi, R., & Farhadi, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00643 · Cited by 170
PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer
Jiang, W., Liu, S., Gao, C., Cao, J., He, R., Feng, J., & Yan, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00524 · Cited by 169
ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
Li, C., Liu, H., Chen, C., Pu, Y., Chen, L., Henao, R., & Carin, L. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.01215 · Cited by 168 · cited 2×
“It is proved that cycle-consistency is an upper bound of the conditional entropy [158].”
BackgroundMescheder, L., Nowozin, S., & Geiger, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.10461 · Cited by 165 · cited 1×
“Algorithmic viewpoint: The numerics of common algorithms for training GANs are analyzed and a new algorithm that has better convergence properties is proposed in [303].”
BackgroundKBGAN: Adversarial Learning for Knowledge Graph Embeddings
Cai, L., & Wang, W. Y. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1133 · Cited by 164 · cited 1×
“Kbgan [386] is proposed to generate high-quality negative examples and used in knowledge graph embeddings.”
BackgroundNo Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling
Wang, X., Chen, W., Wang, Y.-F., & Wang, W. Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1083 · Cited by 161 · cited 1×
“Adversarial REward Learning (AREL) [387] is proposed for visual storytelling.”
BackgroundWasserstein Divergence for GANs
Wu, J., Huang, Z., Thoma, J., Acharya, D., & Van Gool, L. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01228-1_40 · Cited by 160 · cited 2×
“[171] introduce a Wasserstein divergence objective for GANs (WGAN-div), which can faithfully approximate W-div by optimization.”
BackgroundMethodTraining generative neural networks via Maximum Mean Discrepancy optimization
Dziugaite, G. K., Roy, D. M., & Ghahramani, Z. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.03906 · Cited by 159 · cited 1×
“MMD has been used for deep generative models [166]–[168] and model criticism [169].”
MethodShow, Adapt and Tell: Adversarial Training of Cross-Domain Image Captioner
Chen, T.-H., Liao, Y.-H., Chuang, C.-Y., Hsu, W.-T., Fu, J., & Sun, M. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.64 · Cited by 158
Representation Learning by Rotating Your Faces
Tran, L., Yin, X., & Liu, X. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2868350 · Cited by 158 · cited 2×
“Field Subfield Method Super-resolution SRGAN [63], ESRGAN [64], Cycle-in-Cycle GANs [65], SRDGAN [66], TGAN [67] DR-GAN [68], TP-GAN [69], PG2 [70], PSGAN [71], Image synthesis and manipulation APDrawingGAN [72], IGAN [73], Image processing and computer vision introspective adversarial networks [74], GauGAN [75] Textu…”
BackgroundDSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction
Qin, P., Xu, W., & Wang, W. Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1046 · Cited by 158 · cited 1×
“DSGAN [388] is proposed for distant supervision relation extraction.”
BackgroundLearning in Implicit Generative Models
Mohamed, S., & Lakshminarayanan, B. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.03483 · Cited by 157 · cited 1×
“[312] frame GANs within the algorithms for learning in implicit generative models that only specify a stochastic procedure with which to generate data.”
BackgroundAttribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks
Liu, Y., Li, Q., & Sun, Z. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01215 · Cited by 156 · cited 1×
“Face generation [332]–[340] is somewhat easy because there is only one class of object.”
BackgroundSelf-citationGAN Dissection: Visualizing and Understanding Generative Adversarial Networks
Bau, D. A., Zhu, J.-Y., Strobelt, H., Zhou, B., Tenenbaum, J. B., Freeman, W. T., & Torralba, A. B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.10597 · Cited by 154 · cited 1×
“[125] present an analytic framework to visualize and understand GANs.”
BackgroundGenerative Models and Model Criticism via Optimized Maximum Mean Discrepancy
Sutherland, D. J., Tung, H.-Y. F., Strathmann, H., De, S., Ramdas, A., Smola, A. J., & Gretton, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.04488 · Cited by 151 · cited 1×
“MMD has been used for deep generative models [166]–[168] and model criticism [169].”
MethodAPE-GAN: Adversarial Perturbation Elimination with GAN
Jin, G., Shen, S., Zhang, D., Dai, F., & Zhang, Y. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8683044 · Cited by 151 · cited 1×
“To be against adversarial attacks [118], [119], references [120], [121] utilize GANs to conduct the right defense.”
BackgroundGenerating Handwritten Chinese Characters Using CycleGAN
Chang, B., Zhang, Q., Pan, S., & Meng, L. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00028 · Cited by 150 · cited 1×
“[309], [310], [311], [312], [313], [314], [315], [316], to generate neural networks [317], to augment data [318], [319], to learn spatial representations [320], and in network embedding [321], heterogeneous information networks [322], and”
BackgroundOn distinguishability criteria for estimating generative modelsPreprint
Goodfellow, I. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.6515 · Cited by 148 · cited 2×
“where σ is the logistic sigmoid function, equals minimizing (1) [123].”
BackgroundAdversarial Examples that Fool both Computer Vision and Time-Limited Humans
Elsayed, G. F., Shankar, S., Cheung, B., Papernot, N., Kurakin, A., Goodfellow, I., & Sohl‐Dickstein, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.08195 · Cited by 147 · cited 1×
“Adversarial examples [96], [97], [98], [99], [100], [101], [102], [103], [104], [105] also involve the adversarial idea.”
ProGAN: Network Embedding via Proximity Generative Adversarial Network
Gao, H., Pei, J., & Huang, H. (2019) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3292500.3330866 · Cited by 145 · cited 1×
“Data science: GANs have been used in data generating [214], [418]–[426], neural networks generating [427], data augmentation [428], [429], spatial representation learning [430], network embedding [431], heterogeneous information networks [432], and mobile user profiling [433].”
MethodAdversarial Ranking for Language Generation
Lin, K., Li, D., He, X., Zhang, Z., & Sun, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.11001 · Cited by 141 · cited 2×
“Field Subfield Method Super-resolution SRGAN [63], ESRGAN [64], Cycle-in-Cycle GANs [65], SRDGAN [66], TGAN [67] DR-GAN [68], TP-GAN [69], PG2 [70], PSGAN [71], Image synthesis and manipulation APDrawingGAN [72], IGAN [73], Image processing and computer vision introspective adversarial networks [74], GauGAN [75] Textu…”
BackgroundMethodOn the Convergence and Robustness of Training GANs with Regularized Optimal TransportPreprint
Sanjabi, M., Ba, J. L., Razaviyayn, M., & Lee, J. D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.08249 · Cited by 140 · cited 1×
“The convergence and robustness of training GANs with regularized optimal transport is disscussed in [314].”
BackgroundRenderGAN: Generating Realistic Labeled Data
Sixt, L., Wild, B., & Landgraf, T. (2018) · Frontiers in Robotics and AI · doi:10.3389/frobt.2018.00066 · Cited by 138 · cited 1×
“[309], [310], [311], [312], [313], [314], [315], [316], to generate neural networks [317], to augment data [318], [319], to learn spatial representations [320], and in network embedding [321], heterogeneous information networks [322], and”
BackgroundEnhancing Collaborative Filtering with Generative Augmentation
Wang, Q., Yin, H., Wang, H., Nguyen, Q. V. H., Huang, Z. H., & Cui, L. (2019) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3292500.3330873 · Cited by 137 · cited 1×
“Data science: GANs have been used in data generating [214], [418]–[426], neural networks generating [427], data augmentation [428], [429], spatial representation learning [430], network embedding [431], heterogeneous information networks [432], and mobile user profiling [433].”
MethodUsing Wasserstein Generative Adversarial Networks for the design of Monte Carlo simulations
Athey, S. C., Imbens, G. W., Metzger, J., & Munro, E. (2021) · Journal of Econometrics · doi:10.1016/j.jeconom.2020.09.013 · Cited by 132
Eye In-painting with Exemplar Generative Adversarial Networks
Dolhansky, B., & Ferrer, C. C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00824 · Cited by 131
End-to-End Single Image Fog Removal Using Enhanced Cycle Consistent Adversarial Networks
Liu, W., Hou, X., Duan, J., & Qiu, G. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3007844 · Cited by 129 · cited 1×
“GANs have been utilized in other image processing and computer vision tasks [354]–[357] such as object transfiguration [358], [359], semantic segmentation [360], visual saliency prediction [361], object tracking [362], [363], image dehazing [364]–[366], natural image matting [367], image inpainting [368], [369], image…”
Method“High-quality nonparallel voice conversion based on cycle-consistent adversarial network,”
Fang, F., Yamagishi, J., Echizen, I., & Lorenzo-Trueba, J. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8462342 · Cited by 128
PacGAN: The Power of Two Samples in Generative Adversarial Networks
Lin, Z., Khetan, A., Fanti, G., & Oh, S. (2020) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2020.2983071 · Cited by 122 · cited 1×
“For example, PACGAN [305] eases the pain of mode collapse by changing input to the discriminator.”
BackgroundSemantically Decomposing the Latent Spaces of Generative Adversarial NetworksPreprint
Donahue, C., Lipton, Z. C., Balsubramani, A., & McAuley, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.07904 · Cited by 120 · cited 1×
“Face generation [19], [227], [228], [229], [230], [231], [232], [233] is relatively easy because the problem includes only one class of objects.”
BackgroundPsgan: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening
Liu, X., Wang, Y., & Liu, Q. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451049 · Cited by 119
An Adversarial Approach to Hard Triplet Generation
Zhao, Y., Jin, Z., Qi, G.-J., Lu, H., & Hua, X. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01240-3_31 · Cited by 116 · cited 1×
“There are many papers related to GANs [114], [115], [116], [117], [118], [119], [120], [121], [122], [123], [124], [125], [126],”
Do GANs learn the distribution? Some Theory and Empirics
Arora, S., Risteski, A., & Zhang, Y. (2018) · International Conference on Learning Representations · Cited by 110
Task-Oriented GAN for PolSAR Image Classification and Clustering
Liu, F., Jiao, L., & Tang, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2885799 · Cited by 108 · cited 1×
“GANs have been utilized in other image processing and computer vision tasks [354]–[357] such as object transfiguration [358], [359], semantic segmentation [360], visual saliency prediction [361], object tracking [362], [363], image dehazing [364]–[366], natural image matting [367], image inpainting [368], [369], image…”
MethodSynthesizing Audio with Generative Adversarial Networks
Donahue, C., McAuley, J., & Puckette, M. (2018) · Cited by 107
TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
Dash, A., Gamboa, J. C. B., Ahmed, S., Liwicki, M., & Afzal, M. Z. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.06412 · Cited by 105 · cited 1×
“[90] learn text-to-image generation by redescription and text conditioned auxiliary classifier GAN (TAC-GAN) [390] is also proposed for text to image.”
BackgroundLearning Graph Representation With Generative Adversarial Nets
Wang, H., Wang, J., Wang, J., Zhao, M., Zhang, W., Zhang, F., Li, W., Xie, X., & Guo, M. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2961882 · Cited by 105 · cited 1×
“There are many papers related to GANs [114], [115], [116], [117], [118], [119], [120], [121], [122], [123], [124], [125], [126],”
Detecting Deceptive Reviews Using Generative Adversarial Networks
Aghakhani, H., Machiry, A., Nilizadeh, S., Kruegel, C., & Vigna, G. (2018) · 2018 IEEE Security and Privacy Workshops (SPW) · doi:10.1109/spw.2018.00022 · Cited by 104
Towards High Fidelity Face Frontalization in the Wild
Cao, J., Hu, Y., Zhang, H., He, R., & Sun, Z. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-019-01229-6 · Cited by 104
Self-citationDeep Future Gaze: Gaze Anticipation on Egocentric Videos Using Adversarial Networks
Zhang, M., Ma, K. T., Lim, J. H., Zhao, Q., & Feng, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.377 · Cited by 103 · cited 1×
“GANs have also been used for anticipating where people will look [374], [375].”
MethodOn gradient regularizers for MMD GANsPreprint
Arbel, M., Sutherland, D. J., Bińkowski, M., & Gretton, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.11565 · Cited by 102 · cited 1×
“The MMD has been widely used for GANs [170], [171], [172], [173], [174], [175], [176], [177].”
MethodTET-GAN: Text Effects Transfer via Stylization and Destylization
Yang, S., Liu, J., Wang, W., & Guo, Z. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33011238 · Cited by 99
Zhang, Y., Fu, Y., Wang, P., Li, X., & Zheng, Y. (2019) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3292500.3330972 · Cited by 99
EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals
Hartmann, K. G., Schirrmeister, R. T., & Tonio Ball, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.01875 · Cited by 99 · cited 1×
“Additionally, GANs have made achievements in sequential data tasks, such as those involving natural language, music, speech, voice [268], [269], and time series data [270], [271], [272], [273].”
BackgroundWavelet Domain Generative Adversarial Network for Multi-scale Face Hallucination
Huang, H., He, R., Sun, Z., & Tan, T. N. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-019-01154-8 · Cited by 98 · cited 1×
“There are methods specific for face SR [317]–[319].”
MethodSelf-citationMany Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
Fedus, W., Rosca, M., Lakshminarayanan, B., Dai, A. M., Mohamed, S., & Goodfellow, I. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.08446 · Cited by 96 · cited 1×
“References [30], [223] used MS-SSIM to measure the diversity of fake data.”
MethodIt Takes (Only) Two: Adversarial Generator-Encoder Networks
Ulyanov, D., Vedaldi, A., & Lempitsky, V. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11449 · Cited by 95 · cited 11×
“Combination of a generator and an encoder: Different from previous hybrids of autoencoders and GANs, Adversarial Generator-Encoder (AGE) Network [42] is set up directly between the generator and the encoder, and no external mappings are trained in the learning process.”
BackgroundInfluentialGlobal Versus Localized Generative Adversarial Nets
Qi, G.-J., Zhang, L., Hu, H., Edraki, M., Wang, J., & Hua, X. (2018) · 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/cvpr.2018.00164 · Cited by 95
Coupled Generative Adversarial Networks
Liu, M.-Y., & Tuzel, O. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.07536 · Cited by 95 · cited 9×
“Which generator was utilized? shared parameter (c) MGAN ⋯shared weight⋯ ⋯⋯ ⋯⋯ ⋯⋯shared weight Generators Discriminators (d) CoGAN Fig.”
BackgroundMethodInfluentialGenerating and designing DNA with deep generative models
Killoran, N., Lee, L. J., Delong, A., Duvenaud, D., & Frey, B. J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.06148 · Cited by 95 · cited 1×
“Medical field: GANs have been widely utilized in medical field such as generating and designing DNA [404], [405], drug discovery [406], generating multi-label discrete patient records [407], medical image processing [408]–[415], dental restorations [416], and doctor recommendation [417].”
MethodRobustness of Conditional GANs to Noisy LabelsPreprint
Thekumparampil, K. K., Khetan, A., Lin, Z., & Oh, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.03205 · Cited by 91 · cited 1×
“[149] discussed the robustness of conditional GANs to noisy labels.”
BackgroundUnderstanding GANs in the LQG Setting: Formulation, Generalization and Stability
Feizi, S., Farnia, F., Ginart, T., & Tse, D. N. C. (2020) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2020.2991375 · Cited by 90 · cited 1×
“There are many papers related to GANs [114], [115], [116], [117], [118], [119], [120], [121], [122], [123], [124], [125], [126],”
ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity?
Benhenda, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.08227 · Cited by 88 · cited 1×
“Medical field: GANs have been widely utilized in medical field such as generating and designing DNA [404], [405], drug discovery [406], generating multi-label discrete patient records [407], medical image processing [408]–[415], dental restorations [416], and doctor recommendation [417].”
MethodWav2Pix: Speech-conditioned Face Generation Using Generative Adversarial Networks
Duarte, A., Roldan, F., Tubau, M., Escur, J., Pascual, S., Salvador, A., Mohedano, E., McGuinness, K., Torres, J., & Giro-i-Nieto, X. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8682970 · Cited by 88
Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
Karacan, L., Akata, Z., Erdem, A., & Erdem, E. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.00215 · Cited by 87 · cited 1×
“cGANs have been used for convolutional face generation [142], face aging [143], image translation [144], synthesizing outdoor images having specific scenery attributes [145], natural image description [146], and 3D-aware scene manipulation [147].”
MethodDonahue, C., McAuley, J., & Puckette, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.04208 · Cited by 87 · cited 1×
“Additionally, GANs have made achievements in sequential data tasks, such as those involving natural language, music, speech, voice [268], [269], and time series data [270], [271], [272], [273].”
BackgroundTell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction
El-Nouby, A., Sharma, S., Schulz, H., Hjelm, R. D., Asri, L. E., Kahou, S. E., Bengio, Y., & Taylor, G. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01040 · Cited by 86 · cited 1×
“Data science: GANs have been used in data generating [214], [418]–[426], neural networks generating [427], data augmentation [428], [429], spatial representation learning [430], network embedding [431], heterogeneous information networks [432], and mobile user profiling [433].”
MethodHierarchical Implicit Models and Likelihood-Free Variational Inference
Tran, D., Ranganath, R., & Blei, D. M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.08896 · Cited by 86 · cited 2×
“GANs’ Representative variants InfoGAN [14], cGANs [15], CycleGAN [16], f -GAN [17], WGAN [18], WGAN-GP [19], LS-GAN [20] Objective function LSGANs [21], [22], hinge loss based GAN [23]–[25], MDGAN [26], unrolled GAN [27], SN-GANs [23], RGANs [28] Skills ImprovedGANs [29], AC-GAN [30] LAPGAN [31], DCGANs [32], PGGAN [3…”
BackgroundMethodStabilizing Adversarial Nets With Prediction MethodsPreprint
Yadav, A. K., Shah, S., Xu, Z., Jacobs, D. W., & Goldstein, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.07364 · Cited by 83 · cited 1×
“[180] stabilized GANs with prediction methods.”
HyperGAN: A Generative Model for Diverse, Performant Neural NetworksPreprint
Ratzlaff, N., & Li, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.11058 · Cited by 81 · cited 1×
“Data science: GANs have been used in data generating [214], [418]–[426], neural networks generating [427], data augmentation [428], [429], spatial representation learning [430], network embedding [431], heterogeneous information networks [432], and mobile user profiling [433].”
MethodGenerative Adversarial Trainer: Defense to Adversarial Perturbations with GAN
Lee, H., Han, S., & Lee, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.03387 · Cited by 80 · cited 1×
“To be against adversarial attacks [118], [119], references [120], [121] utilize GANs to conduct the right defense.”
BackgroundAdversarial Substructured Representation Learning for Mobile User Profiling
Wang, P., Fu, Y., Xiong, H., & Li, X. (2019) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3292500.3330869 · Cited by 78 · cited 1×
“Data science: GANs have been used in data generating [214], [418]–[426], neural networks generating [427], data augmentation [428], [429], spatial representation learning [430], network embedding [431], heterogeneous information networks [432], and mobile user profiling [433].”
MethodCo-Evolutionary Compression for Unpaired Image Translation
Shu, H., Wang, Y., Jia, X., Han, K., Chen, H., Xu, C., Tian, Q., & Xu, C. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00333 · Cited by 78 · cited 1×
“GANs have been widely used in many other areas such as malware detection [434], chess game playing [435], steganography [436]–[439], privacy-preserving [440]–[442], social robot [443], and network pruning [444], [445].”
MethodApproximability of Discriminators Implies Diversity in GANsPreprint
Bai, Y. D., Ma, T., & Risteski, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.10586 · Cited by 77 · cited 1×
“[307] show that GANs can in principle learn distributions in Wasserstein distance (or KL-divergence in many situations) with polynomial sample complexity, if the discriminator class has strong discriminating power against the particular generator class (instead of against all possible generators).”
BackgroundLearning Plannable Representations with Causal InfoGAN
Kurutach, T., Tamar, A., Yang, G., Russell, S., & Abbeel, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.09341 · Cited by 76 · cited 7×
“(16) By comparing (15) and (16), we can see that the generator of InfoGAN is similar to that of cGANs.”
MethodInfluentialGenerative Adversarial Trainer Defense to Adversarial Perturbations with GAN
이형일 (2020) · Seoul National University Open Repository (Seoul National University) · Cited by 75
Achieving Causal Fairness through Generative Adversarial Networks
Xu, D., Wu, Y., Yuan, S., Zhang, L., & Wu, X. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/201 · Cited by 74 · cited 2×
“Data science: GANs have been used in data generating [214], [418]–[426], neural networks generating [427], data augmentation [428], [429], spatial representation learning [430], network embedding [431], heterogeneous information networks [432], and mobile user profiling [433].”
MethodGenerative Semantic Manipulation with Mask-Contrasting GAN
Liang, X., Zhang, H., Lin, L., & Xing, E. P. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01261-8_34 · Cited by 73 · cited 1×
“GANs have been utilized in other image processing and computer vision tasks [354]–[357] such as object transfiguration [358], [359], semantic segmentation [360], visual saliency prediction [361], object tracking [362], [363], image dehazing [364]–[366], natural image matting [367], image inpainting [368], [369], image…”
MethodDoes the Wake-sleep Algorithm Produce Good Density Estimators?
Frey, B. J., Hinton, G. E., & Dayan, P. (1995) · UCL Discovery (University College London) · Cited by 73
Are GANs Created Equal? A Large-Scale Study
Lučić, M., Kurach, K., Michalski, M., Gelly, S., & Bousquet, O. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.10337 · Cited by 73 · cited 1×
“There are some other comparative study of GANs such as [226].”
Generative Adversarial Networks Conditioned on Brain Activity Reconstruct Seen Images
St-Yves, G., & Naselaris, T. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00187 · Cited by 72
Quantitatively Evaluating GANs With Divergences Proposed for TrainingPreprint
Im, D. J., Ma, H., Taylor, G. W., & Branson, K. M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.01045 · Cited by 72 · cited 1×
“[161] quantitatively evaluated GANs with divergences proposed for training.”
BackgroundImproving MMD-GAN Training with Repulsive Loss FunctionPreprint
Wang, W., Sun, Y., & Halgamuge, S. K. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.09916 · Cited by 72 · cited 1×
“The MMD has been widely used for GANs [170], [171], [172], [173], [174], [175], [176], [177].”
MethodCSGAN: Cyclic-Synthesized Generative Adversarial Networks for image-to-image transformation
Babu, K. K., & Dubey, S. R. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114431 · Cited by 68
Dual Variational Generation for Low-Shot Heterogeneous Face RecognitionPreprint
Fu, C., Wu, X., Hu, Y., Huang, H., & He, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.10203 · Cited by 67 · cited 1×
“Face generation [19], [227], [228], [229], [230], [231], [232], [233] is relatively easy because the problem includes only one class of objects.”
BackgroundA Convex Duality Framework for GANsPreprint
Farnia, F., & Tse, D. (2018) · Neural Information Processing Systems · doi:10.48550/arxiv.1810.11740 · Cited by 66 · cited 1×
“There are many papers related to GANs [114], [115], [116], [117], [118], [119], [120], [121], [122], [123], [124], [125], [126],”
3D Aided Duet GANs for Multi-View Face Image Synthesis
Cao, J., Hu, Y., Yu, B., He, R., & Sun, Z. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2891116 · Cited by 64 · cited 1×
“Face generation [19], [227], [228], [229], [230], [231], [232], [233] is relatively easy because the problem includes only one class of objects.”
BackgroundSelf-citationA survey on generative adversarial network-based text-to-image synthesis
Zhou, R. H., Jiang, C. F., & Xu, Q. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.04.069 · Cited by 61 · cited 1×
“targeted the use of GANs for specific applications, such as image synthesis and editing [8], text-toimage synthesis [9], and audio enhancement and synthesis [10].”
BackgroundTag Disentangled Generative Adversarial Network for Object Image Re-rendering
Wang, C., Wang, C., Xu, C., & Tao, D. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/404 · Cited by 59 · cited 1×
“GANs have also been used in other face related applications such as facial attribute changes [327] and portrait editing [328]– [331].”
MethodSelf-citationLu, S., Dou, Z., Xu, J., Nie, J., & Wen, J.-R. (2019) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3331184.3331218 · Cited by 58 · cited 2×
“Field Subfield Method Super-resolution SRGAN [63], ESRGAN [64], Cycle-in-Cycle GANs [65], SRDGAN [66], TGAN [67] DR-GAN [68], TP-GAN [69], PG2 [70], PSGAN [71], Image synthesis and manipulation APDrawingGAN [72], IGAN [73], Image processing and computer vision introspective adversarial networks [74], GauGAN [75] Textu…”
BackgroundGeneGAN: Learning Object Transfiguration and Object Subspace from Unpaired Data
Zhou, S., Xiao, T., Yang, Y. M., Feng, D., He, Q., & He, W. (2017) · British Machine Vision Conference (BMVC) · doi:10.5244/c.31.111 · Cited by 58
Arbitrary Talking Face Generation via Attentional Audio-Visual Coherence Learning
Zhu, H., Huang, H., Li, Y., Zheng, A., & He, R. (2020) · Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/327 · Cited by 58 · cited 1×
“Specific methods have been designed for face SR [212], [213], [214].”
MethodUnsupervised Cipher Cracking Using Discrete GANsPreprint
Gomez, A. N., Huang, S., Zhang, I., Li, B. M., Osama, M., & Kaiser, Ł. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.04883 · Cited by 57 · cited 1×
“[330], [331], social robots [332], and network pruning”
BackgroundGuiding InfoGAN with Semi-supervision
Spurr, A., Aksan, E., & Hilliges, O. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-71249-9_8 · Cited by 51 · cited 1×
“InfoGAN has several variants, such as causal InfoGAN [129] and semi-supervised InfoGAN (ss-InfoGAN) [130].”
Semi-supervised Conditional GANsPreprint
Sricharan, K., Bala, R., Shreve, M., Ding, H., Saketh, K., & Sun, J. H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.05789 · Cited by 50 · cited 1×
“Discriminators of most cGANs based methods [31], [41], [152]–[154] feed conditional information y into the discriminator by simply concatenating (embedded) y to the input or to the feature vector at some middle layer.”
MethodAdversarial Training for Sketch Retrieval
Creswell, A., & Bharath, A. A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46604-0_55 · Cited by 49 · cited 1×
“[373] show that the representations learned by GANs can also be used for retrieval.”
BackgroundGenerative Multi-Adversarial Networks
Durugkar, I., Gemp, I., & Mahadevan, S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01673 · Cited by 48
Liu, B., Fu, J., Kato, M. P., & Yoshikawa, M. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240587 · Cited by 47 · cited 1×
“Furthermore, GANs have been widely utilized in other NLP applications such as question answer selection [393], [394], poetry generation [395], talent-job fit [396], and review detection and geneneration [397], [398].”
MethodGenerative Adversarial Nets from a Density Ratio Estimation Perspective
Uehara, M., Sato, I., Suzuki, M., Nakayama, K., & Matsuo, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.02920 · Cited by 46 · cited 1×
“[162] extend the f -GAN further, where the f -divergence is directly minimized in the generator step and the ratio of the distributions of real and generated data are predicted in the discriminator step.”
BackgroundDeconstructing Generative Adversarial Networks
Zhu, B., Jiao, J., & Tse, D. N. C. (2020) · IEEE Transactions on Information Theory · doi:10.1109/tit.2020.2983698 · Cited by 44 · cited 1×
“There are many papers related to GANs [126]–[131] such as CSGAN [132] and LOGAN [133].”
BackgroundA Layer-Based Sequential Framework for Scene Generation with GANs
Turkoglu, M. O., Thong, W., Spreeuwers, L., & Kicanaoglu, B. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018901 · Cited by 41
GAN-based Enhanced Deep Subspace Clustering Networks
Yu, Z., Zhang, Z., Cao, W., Liu, C., Chen, J. P., & Wong, H. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.3025301 · Cited by 41 · cited 1×
“There are many papers related to GANs [114], [115], [116], [117], [118], [119], [120], [121], [122], [123], [124], [125], [126],”
Rare Query Expansion Through Generative Adversarial Networks in Search Advertising
Lee, M.-C., Gao, B., & Zhang, R. (2018) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3219819.3219850 · Cited by 35
Luo, Y., Zhang, H., Wen, Y., & Zhang, X. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3357899 · Cited by 35 · cited 1×
“Furthermore, GANs have been widely utilized in other NLP applications such as question answer selection [393], [394], poetry generation [395], talent-job fit [396], and review detection and geneneration [397], [398].”
MethodSelf-citationHow Well Generative Adversarial Networks Learn DistributionsPreprint
Liang, T. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3714011 · Cited by 29 · cited 1×
“[205] studied how well GANs learn densities, including nonparametric and parametric target distributions.”
BackgroundHan, Y., Zhang, P., Huang, W., Zha, Y., Cooper, G. D., & Zhang, Y. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.107027 · Cited by 27 · cited 1×
“[253], [254], image dehazing [255], [256], [257], natural”
Robust Conditional Generative Adversarial NetworksPreprint
Chrysos, G. G., Kossaifi, J., & Zafeiriou, S. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.08657 · Cited by 27
Audio Enhancement and Synthesis using Generative Adversarial Networks: A Survey
Torres-Reyes, N., & Latifi, S. (2019) · International Journal of Computer Applications · doi:10.5120/ijca2019918334 · Cited by 24 · cited 1×
“1) GANs for specific applications: There are surveys of using GANs for specific applications such as image synthesis and editing [5], audio enhancement and synthesis [6].”
BackgroundAdversarial Training for Community Question Answer Selection Based on Multi-Scale Matching
Xiao, Y., Khabsa, M., Wang, M., Wang, W., Awadallah, A. H., Kifer, D., & Giles, C. L. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.3301395 · Cited by 23
Generating images with recurrent adversarial networks
Im, D. J., Kim, C. D., Jiang, H., & Memisevic, R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.05110 · Cited by 23 · cited 1×
“[344] generated images with recurrent adversarial networks.”
Generative Adversarial Networks: Recent Developments
Zamorski, M., Zdobylak, A., Zięba, M., & Świątek, J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20912-4_24 · Cited by 21
Anticipating Where People will Look Using Adversarial Networks
Zhang, M., Ma, K. T., Lim, J., Zhao, Q., & Feng, J. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2871688 · Cited by 20 · cited 1×
“GANs have also been used for anticipating where people will look [374], [375].”
MethodSRDGAN: learning the noise prior for Super Resolution with Dual Generative Adversarial NetworksPreprint
Guan, J., Pan, C., Li, S., & Yu, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.11821 · Cited by 19 · cited 2×
“Field Subfield Method Super-resolution SRGAN [63], ESRGAN [64], Cycle-in-Cycle GANs [65], SRDGAN [66], TGAN [67] DR-GAN [68], TP-GAN [69], PG2 [70], PSGAN [71], Image synthesis and manipulation APDrawingGAN [72], IGAN [73], Image processing and computer vision introspective adversarial networks [74], GauGAN [75] Textu…”
BackgroundGarbacea, C., Carton, S., Yan, S., & Mei, Q. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1409 · Cited by 18 · cited 1×
“Furthermore, GANs have been widely utilized in other NLP applications such as question answer selection [393], [394], poetry generation [395], talent-job fit [396], and review detection and geneneration [397], [398].”
MethodWu, P., Zheng, C., & Pan, L. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3076766 · Cited by 12 · cited 1×
“There are many papers related to GANs [114], [115], [116], [117], [118], [119], [120], [121], [122], [123], [124], [125], [126],”
Hinton, G. E. (2017) · Springer eBooks · doi:10.1007/978-1-4899-7687-1_31 · Cited by 11
Schmidhuber, J. (2019) · arXiv (Cornell University) · Cited by 8
DRGAN: A GAN-Based Framework for Doctor Recommendation in Chinese On-Line QA Communities
Tian, B., Zhang, Y., Chen, X., Xing, C., & Li, C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-18590-9_63 · Cited by 7 · cited 1×
“Medical field: GANs have been widely utilized in medical field such as generating and designing DNA [404], [405], drug discovery [406], generating multi-label discrete patient records [407], medical image processing [408]–[415], dental restorations [416], and doctor recommendation [417].”
MethodCycle-Consistent Adversarial Learning as Approximate Bayesian InferencePreprint
Tiao, L. C., Bonilla, E. V., & Ramos, F. T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.01771 · Cited by 7 · cited 1×
“CycleGAN can be derived as a special case within the proposed variational inference (VI) framework [159], naturally establishing its relationship with approximate Bayesian inference methods.”
BackgroundTensor Super-Resolution with Generative Adversarial Nets: A Large Image Generation Approach
Ding, Z., Liu, X.-Y., Yin, M., & Kong, L. (2019) · Communications in computer and information science · doi:10.1007/978-981-15-1398-5_15 · Cited by 6 · cited 1×
“Deep tensor generative adversarial nets (TGAN) [55] were proposed to generate large high-quality images by exploring tensor structures.”
BackgroundGenerative Adversarial Network-based Postfiltering for Statistical Parametric Speech Synthesis
Kaneko, T., Kameoka, H., Hojo, N., Ijima, Y., Kaoru, H., & Kashino, K. (2016) · IEICE Technical Report; IEICE Tech. Rep. · Cited by 3
LOGAN: Latent Optimisation for Generative Adversarial Networks
Wu, Y., Donahue, J., Balduzzi, D., Simonyan, K., & Lillicrap, T. (2019) · arXiv · doi:10.48550/arxiv.1912.00953 · cited 1×
“There are many papers related to GANs [126]–[131] such as CSGAN [132] and LOGAN [133].”
Background
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
BAİDOO-ANU, D., & OWUSU ANSAH, L. (2023) · Journal of AI · doi:10.61969/jai.1337500 · Cited by 3,939
Diffusion Models: A Comprehensive Survey of Methods and Applications
Yang, L., Zhang, Z., Song, Y., Hong, S., Xu, R., Zhao, Y., Zhang, W., Cui, B., & Yang, M.-H. (2024) · ACM Computing Surveys · doi:10.1145/3626235 · Cited by 1,704
“Generative Adversarial Networks (GANs) [40, 73, 84] mainly consist of two models: a generatorG and a discriminator D .”
MethodBaidoo-Anu, D., & Owusu Ansah, L. (2023) · doi:10.2139/ssrn.4337484 · Cited by 3,004
“Extant literature has identified two major generative AI ⎼ Generative Adversarial Network (GAN) and Generative Pre-trained Transformer (GPT) (Abukmeil, et al., 2021; Bro wn et al., 2020; Hu, 2022; Jovanović, 2022; Gui, et al., 2021).”
BackgroundGenerative Adversarial Networks (GANs): Challenges, Solutions, and Future Directions
Saxena, D., & Cao, J. (2022) · ACM Computing Surveys · doi:10.1145/3446374 · Cited by 689
“VAE-GAN [72], AAE [73], AVB [74], ASVAE [75], MDGAN [40], Dist-GAN [76], α-GAN [25] Latent space autoencoder (S 13 (ii)) ALI [77], BiGAN [78], DALI [79], CV-BiGAN [80], MV-BiGAN [80], HALI [81], AGE [82], VEEGAN [83], MGGAN [84] Improved D (S 14 ) EBGAN [85], BEGAN [86], MAGAN [87], [88],…”
MethodInfluentialBond-Taylor, S., Leach, A., Long, Y., & Willcocks, C. G. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3116668 · Cited by 703
“[175], generative adversarial networks [70], [249], and energy-based models [202], however, naturally these dive into the intricacies of their respective method rather than”
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.