Synonyms
Definition
Generative adversarial network (GAN) is a framework that was invented for the purpose of creating an artificial distribution that mimics a given target distribution, and it consists of a generator function that produces the imitator distribution from a seed prior and a discriminator function that distinguishes the artificial distribution from the target.
Background
The task of approximating the probability density from empirically collected dataset (i.e., the training dataset)–or, in short, the task of learning a generative model–is a central problem of machine learning. The most straightforward way of carrying out this task is the method of maximum likelihood estimation (MLE). However, a naive application of MLE with arbitrary choice of models won’t suffice. For the learning of a complex probability distribution like...
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arjovsky M, Bottou L (2017) Towards principled methods for training generative adversarial networks. In: ICLR
Baram N, Anschel O, Caspi I, Mannor S (2017) End-to-end differentiable adversarial imitation learning. In: International conference on machine learning, pp 390–399
Bińkowski M, Sutherland DJ, Arbel M, Gretton A (2018) Demystifying MMD GANs. arXiv preprint arXiv:1801.01401
Brock A, Donahue J, Simonyan K (2018) Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096
Fedus W, Rosca M, Lakshminarayanan B, Dai AM, Mohamed S, Goodfellow I (2017) Many paths to equilibrium: GANs do not need to decrease adivergence at every step. arXiv preprint arXiv:1710.08446
Finn C, Christiano P, Abbeel P, Levine S (2016) A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models. arXiv preprint arXiv:1611.03852
Fu J, Luo K, Levine S (2017) Learning robust rewards with adversarial inverse reinforcement learning. arXiv preprint arXiv:1710.11248
Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: NIPS, pp 2672–2680
Gutmann MU, Hyvärinen A (2012) Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics. J Mach Learn Res 13 : 307–361
Heusel M, Ramsauer H, Unterthiner T, Nessler B, Klambauer G, Hochreiter S (2017) GANs trained by a two time-scale update rule converge to a nash equilibrium. arXiv preprint arXiv:1706.08500
Hyvärinen A (2005) Estimation of non-normalized statistical models by score matching. J Mach Learn Res 6 : 695–709
Karras T, Aila T, Laine S, Lehtinen J (2017) Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196
Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114
Larochelle H, Murray I (2011) The neural autoregressive distribution estimator. In: AISTATS, pp 29–37
Li C-L, Chang W-C, Cheng Y, Yang Y, Póczos B (2017) MMD GAN: Towards deeper understanding of moment matching network. In: Advances in neural information processing systems, pp 2203–2213
Li Y, Swersky K, Zemel R (2015) Generative moment matching networks. In: International conference on machine learning, pp 1718–1727
Lucic M, Kurach K, Michalski M, Gelly S, Bousquet O (2018) Are GANs created equal? a large-scale study. In: Advances in neural information processing systems, pp 698–707
Mescheder L, Geiger A, Nowozin S (2018) Which training methods for GANs do actually converge? In: International conference on machine learning, pp 3478–3487
Metz L, Poole B, Pfau D, Sohl-Dickstein J (2016) Unrolled generative adversarial networks. arXiv preprint arXiv:1611.02163
Miyato T, Kataoka T, Koyama M, Yoshida Y (2018) Spectral normalization for generative adversarial networks. In: ICLR
Mohamed S, Lakshminarayanan B (2016) Learning in implicit generative models. arXiv preprint arXiv:1610.03483
Nowozin S, Cseke B, Tomioka R (2016) f-GAN: training generative neural samplers using variational divergence minimization. In: NIPS, pp 271–279
Radford A, Metz L, Chintala S (2016) Unsupervised representation learning with deep convolutional generative adversarial networks. In: ICLR
Rezende DJ, Mohamed S (2015) Variational inference with normalizing flows. arXiv preprint arXiv:1505.05770
Saito M, Saito S (2018) Tganv2: efficient training of large models for video generation with multiple subsampling layers. arXiv preprint arXiv:1811.09245
Salimans T, Goodfellow I, Zaremba W, Cheung V, Radford A, Chen X (2016) Improved techniques for training GANs. In: NIPS, pp 2226–2234
Sriperumbudur BK, Gretton A, Fukumizu K, Schölkopf B, Lanckriet GRG (2010) Hilbert space embeddings and metrics on probability measures. J Mach Learn Res 11 : 1517–1561
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: CVPR, pp 1–9
Yamaguchi S, Koyama M (2019) Distributional concavity regularization for GANs. In: International conference on learning representations
Zhu J-Y, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer International Publishing
About this entry
Cite this entry
Miyato, T., Koyama, M. (2021). Generative Adversarial Network (GAN). In: Ikeuchi, K. (eds) Computer Vision. Springer, Cham. https://doi.org/10.1007/978-3-030-63416-2_860
Download citation
DOI: https://doi.org/10.1007/978-3-030-63416-2_860
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63415-5
Online ISBN: 978-3-030-63416-2
eBook Packages: Computer ScienceReference Module Computer Science and Engineering