How Generative Adversarial Networks and Their Variants Work
Top Cited Papers
- 13 February 2019
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 52 (1), 1-43
- https://doi.org/10.1145/3301282
Abstract
Generative Adversarial Networks (GANs) have received wide attention in the machine learning field for their potential to learn high-dimensional, complex real data distribution. Specifically, they do not rely on any assumptions about the distribution and can generate real-like samples from latent space in a simple manner. This powerful property allows GANs to be applied to various applications such as image synthesis, image attribute editing, image translation, domain adaptation, and other academic fields. In this article, we discuss the details of GANs for those readers who are familiar with, but do not comprehend GANs deeply or who wish to view GANs from various perspectives. In addition, we explain how GANs operates and the fundamental meaning of various objective functions that have been suggested recently. We then focus on how the GAN can be combined with an autoencoder framework. Finally, we enumerate the GAN variants that are applied to various tasks and other fields for those who are interested in exploiting GANs for their research.Keywords
Funding Information
- Electrical and Computer Engineering, Seoul National University
- Research and Development of Police science and Technology under Center for Research and Development of Police science and Technology
- Ministry of Science and ICT (2018R1A2B3001628)
- Brain Korea 21 Plus Project
- Korean National Police Agency
- ICT and Future Planning (PA-C000001 and 2016M3A7B4911115)
- National Research Foundation of Korea
This publication has 29 references indexed in Scilit:
- Inverse Reinforcement LearningPublished by Springer Science and Business Media LLC ,2011
- Single-shot detection of bacterial endospores via coherent Raman spectroscopyProceedings of the National Academy of Sciences of the United States of America, 2008
- Image Quality Assessment: From Error Visibility to Structural SimilarityIEEE Transactions on Image Processing, 2004
- Poisson image editingACM Transactions on Graphics, 2003
- The Mahalanobis distanceChemometrics and Intelligent Laboratory Systems, 2000
- Long Short-Term MemoryNeural Computation, 1997
- Kantorovich-Rubinstein norm and its application in the theory of Lipschitz spacesProceedings of the American Mathematical Society, 1992
- A method for enforcing integrability in shape from shading algorithmsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1988
- Information Theory and Statistical MechanicsPhysical Review B, 1957
- On Conjugate Convex FunctionsCanadian Journal of Mathematics, 1949