Synonyms
Related Concepts
Definition
Deep generative models, or deep generator networks, refer to a family of deep networks that take in an input tensor z and then output a sample of certain patterns. In computer vision, such patterns could be specific object categories, such as cats, as shown in Fig. 1. The input tensor z could be as simple as a randomly generated vector. The deep generative model can be trained with a set of images in an unsupervised way. Two popular algorithmic formulations are the generative adversarial networks (GANs) [9] and the variational auto-encoder (VAE) [14].
A deep generative model (a generator network) takes a tensor as an input and outputs a sample following the distribution of certain patterns. The figure presents a generator network for cat images
This is a preview of subscription content, log in via an institution to check access.
References
Ackley DH, Hinton GE, Senjnowski TJ (1985) A learning algorithm for boltzmann machines. Cogn Sci 9(1):147–169
Andrew Blake PK, Rother C (eds) (2011) Markov random fields for vision and image processing. The MIT Press, Cambridge, MA
Bao J, Chen D, Wen F, Li H, Hua G (2018) Towards open-set identity preserving face synthesis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6713–6722
Blei DM, Ng AY, Jordan MI (2003) Latent dirichlet allocation. J Mach Learn Res 3:993–1022
Bloesch M, Czarnowski J, Clark R, Leutenegger S, Davison AJ (2018) Codeslam – learning a compact, optimisable representation for dense visual SLAM. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the em algorithm. J R Stat Soc Ser B (Methodol) 39(1):1–38
Doersch C (2016) Tutorial on variational autoencoders. arXiv, stat.ML 1606.05908
Ghahramani Z, Beal MJ (2001) Graphical models and variational methods. In: Advanced mean field methods – theory and practice. Neural information processing series. MIT Press, Cambridge, MA
Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Ghahramani Z, Welling M, Cortes C, Lawrence ND, Weinberger KQ (eds) Advances in neural information processing systems, vol 27, pp 2672–2680. Curran Associates, Inc.
Gutmann M, Hyvarinen A (2010) Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: Proceedings of international conference on artificial intelligence and statistics, Sardinia
Hinton GE (2002) Training products of experts by minimizing contrastive divergence. Neural Comput 14(8):1771–1800
Hinton GE, Osindero S, whye Teh Y (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554
Karras T, Laine S, Aila T (2019) A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Long Beach
Kingma DP, Welling M (2014) Auto-encoding variational bayes. In: Bengio Y, LeCun Y (eds) Interactional conference on learning representation
LeCun Y, Chopra S, Hadsell R, Ranzato MA, Huang FJ (2006) A tutorial on energy-based learning. In: Predicting structured data. The MIT Press, Cambridge, MA
Peral J, Russell S (2003) Bayesian networks. In: Handbook of brain theory and neural networks. MIT Press, Cambridge, MA, pp 157–160
Rabiner LR (1989) A tutorial on hidden markov models and selected applications in speech recognition. Proc IEEE 77(2):257–286
Schawinski K, Zhang C, Zhang H, Fowler L, Santhanam GK (2017) Generative adversarial networks recover features in astrophysical images of galaxies beyond the deconvolution limit. Mon Not R Astron Soc Lett 467(1):L110–L114
Tu Z (2007) Learning generative models via discriminative approaches. In: Proceedings of IEEE conference on computer vision and pattern recognition, Minneapolis
Zhu J-Y, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE international conference on computer vision
Author information
Authors and Affiliations
Corresponding author
Section Editor information
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this entry
Cite this entry
Hua, G. (2020). Deep Generative Models. In: Computer Vision. Springer, Cham. https://doi.org/10.1007/978-3-030-03243-2_865-1
Download citation
DOI: https://doi.org/10.1007/978-3-030-03243-2_865-1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-03243-2
Online ISBN: 978-3-030-03243-2
eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering