Abstract
Generative Adversarial Networks (GANs) are a class of deep learning algorithms which are based on two neural networks competing with each other. They are capable of learning representations from data that isn’t well annotated and these deep representations can be quite useful in a variety of applications, including image classification, generation, and in deblurring and creating super-resolution images. This paper is an attempt to explore a few different types of GANs, and to discuss issues and solutions in training methods. We also attempt to explore various applications of GANs and the methods we can use these learned deep representations.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Improving neural networks by preventing co-adaptation of feature detectors. Technical report. arXiv:1207.0580 (2012)
Saliman, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: 30th Conference on Neural Information Processing Systems (NIPS) (2016)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434 (2016)
Springenberg, J.T., Dosovitskiy, J., Brox, T., Riedmiller, M.: Striving for simplicity: The all convolutional net. arXiv:1412.6806 (2014)
Mordvintsev, A., Olah, C., Tyka, M.: Inceptionism: going deeper into neural networks. http://googleresearch.blogspot.com/2015/06/ inceptionism-going-deeper-into-neural.html. Accessed 17 June 2015
Vinod, N., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807–814 (2010)
Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the ICML, vol. 28 (2013)
Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. arXiv:1505.00853 (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167 (2015)
Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier gans. arXiv:1610.09585v4 (2017)
Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems 2016, pp. 2172–2180. arXiv:1606.03657v1 [cs.LG] (2016)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv:1411.1784 (2014)
Nguyen, A., Dosovitskiy, A., Yosinski, J., Brox, T., Clune, J.: Synthesizing the preferred inputs for neurons in neural networks via deep generator networks. In: 30th Conference on Neural Information Processing Systems (NIPS), 2016. Advances in Neural Information Processing Systems, pp. 3387–3395 (2016)
Odena, A., Dumoulin, V., Olah, C.: Deconvolution and checkerboard artifacts. Distill 1(10), e3 (2016)
Gao, F., Yang, Y., Wang, J., Sun, J., Yang, E., Zhou, H.: A deep convolutional generative adversarial networks (DCGANS)-based semi-supervised methods for object recognition in synthetic aperture radar (SAR) images. Remote Sens. 10, 846 (2018)
Bas, A., Huner, P., Smith, W.A.P., Awais, M., Kittler, J.: 3D morphable models as spatial transformer networks. arXiv:1708.07199v1 [cs.CV] (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Khursheed, M.O., Saeed, D., Khan, A.M. (2020). Generative Adversarial Networks: A Survey of Techniques and Methods. In: Pandian, A.P., Senjyu, T., Islam, S.M.S., Wang, H. (eds) Proceeding of the International Conference on Computer Networks, Big Data and IoT (ICCBI - 2018). ICCBI 2018. Lecture Notes on Data Engineering and Communications Technologies, vol 31. Springer, Cham. https://doi.org/10.1007/978-3-030-24643-3_58
Download citation
DOI: https://doi.org/10.1007/978-3-030-24643-3_58
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24642-6
Online ISBN: 978-3-030-24643-3
eBook Packages: EngineeringEngineering (R0)