Mathematics and Computer Science
Volume 5, Issue 1, January 2020, Pages: 31-41
Received: Jan. 17, 2020;
Accepted: Feb. 11, 2020;
Published: Mar. 10, 2020
Views 516 Downloads 273
Yi Yin, School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, P. R. China
Lin Ouyang, School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, P. R. China
Zhixiang Wu, School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, P. R. China
Shuifang Yin, School of Science, Wuhan University of Science and Technology, Wuhan, P. R. China
The generative model is a very important type of model in the field of artificial intelligence in recent years. Such models can comprehend the data through the neural network, and then create data according to the probability distribution of the input data, predict the results according to the data characteristics. The whole processing process is "intelligent". At present, two typical applications of generative model are Generative Adversarial Networks (GAN) model and Encoder-Decoder model, which have strong ability to generate image data. In the model of GAN, the generator simulates real data, and the discriminator judges the authenticity of the samples. Its goal is to train a generator to fit the real data perfectly, so that the discriminator cannot distinguish. In the Encoding-Decoding model, it can be understood as a process of "Encoding→intermediate vector→Decoding", It is suitable for processing one kind of data to generate another kind of data with the same probability distribution as the original data. Since most of the data features are intermingled, they are encoded in a complex and disorderly way. But if these features are extractable, it shows that these features are interpretable, and it will be easier to use these features for coding. Based on this situation, some research results have been produced by incorporating the Encoder- Decoder into GAN. This paper systematically analyzes and summarizes the basic concepts and theories of GAN and Encoder-Decoder, as well as their respective advantages and disadvantages. On this basis, by combing the related work of the two types of models, the main technical routes of the three types of GAN based on the Encoder Decoder are summarized, the techniques and theories including variational inference, energy function and correlation transformation of different distribution data are summarized. Finally, the GAN based on the Encoder-Decoder is summarized.
A Survey of Generative Adversarial Networks Based on Encoder-Decoder Model, Mathematics and Computer Science.
Vol. 5, No. 1,
2020, pp. 31-41.
Sabuncu M R, Yeo B T T, Van Leemput K, et al. A generative model for image segmentation based on label fusion [J]. IEEE transactions on medical imaging, 2010, 29 (10): 1714-1729.
Wang C, Chang X, Xin Y, et al. Evolutionary Generative Adversarial Networks [J]. IEEE Transactions on Evolutionary Computation, 2019.
Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets [C]. Advances in neural information processing systems. 2014: 2672-2680.
Badrinarayanan V, Kendall A, Cipolla R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation [J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39 (12): 2481-2495.
Ledig C, Theis L, Huszár F, et al. Photo-realistic single image super-resolution using a generative adversarial network [C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4681-4690.
Denton E L, Chintala S, Fergus R. Deep generative image models using a laplacian pyramid of adversarial networks [C]. Advances in neural information processing systems. 2015: 1486-1494.
Kendall A, Badrinarayanan V, Cipolla R. Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding [J]. arXiv preprint arXiv: 1511.02680, 2015.
Sordoni, Alessandro, Bengio, et al. A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestion [J]. Computer Science, 2015: 553-562.
Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks [C]. Advances in neural information processing systems. 2014: 3104-3112.
Creswell A, White T, Dumoulin V, et al. Generative adversarial networks: An overview [J]. IEEE Signal Processing Magazine, 2018, 35 (1): 53-65.
Zhang H, Goodfellow I, Metaxas D, et al. Self-attention generative adversarial networks [J]. arXiv preprint arXiv: 1805.08318, 2018.
Cho K, Van Merriënboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation [J]. arXiv preprint arXiv: 1406.1078, 2014.
Choi Y, Choi M, Kim M, et al. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 8789-8797.
Alonso-Monsalve S, Whitehead L H. Image-based model parameter optimisation using Model-Assisted Generative Adversarial Networks [J]. arXiv preprint arXiv: 1812.00879, 2018.
Paisley J, Blei D, Jordan M. Variational Bayesian inference with stochastic search [J]. arXiv preprint arXiv: 1206.6430, 2012.
Larsen A B L, Sønderby S K, Larochelle H, et al. Autoencoding beyond pixels using a learned similarity metric [J]. arXiv preprint arXiv: 1512.09300, 2015.
Chen X, Duan Y, Houthooft R, et al. Infogan: Interpretable representation learning by information maximizing generative adversarial nets [C]. Advances in neural information processing systems. 2016: 2172-2180.
Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks [J]. arXiv preprint arXiv: 1511.06434, 2015.
Kurutach T, Tamar A, Yang G, et al. Learning plannable representations with causal infogan [C]. Advances in Neural Information Processing Systems. 2018: 8733-8744.
Dumoulin V, Belghazi I, Poole B, et al. Adversarially learned inference [J]. arXiv preprint arXiv: 1606.00704, 2016.
Donahue J, Krähenbühl P, Darrell T. Adversarial feature learning [J]. arXiv preprint arXiv: 1605.09782, 2016.
Huang H, He R, Sun Z, et al. Introvae: Introspective variational autoencoders for photographic image synthesis [C]. Advances in Neural Information Processing Systems. 2018: 52-63.
Ng A. Sparse autoencoder [J]. CS294A Lecture notes, 2011, 72 (2011): 1-19.
Poultney C, Chopra S, Cun Y L. Efficient learning of sparse representations with an energy-based model [C]. Advances in neural information processing systems. 2007: 1137-1144.
Zhao J, Mathieu M, LeCun Y. Energy-based generative adversarial network [J]. arXiv preprint arXiv: 1609.03126, 2016.
Berthelot D, Schumm T, Metz L. Began: Boundary equilibrium generative adversarial networks [J]. arXiv preprint arXiv: 1703. 10717, 2017.
Liu M Y, Tuzel O. Coupled generative adversarial networks [C]. Advances in neural information processing systems. 2016: 469-477.
Lample G, Zeghidour N, Usunier N, et al. Fader networks: Manipulating images by sliding attributes [C]. Advances in Neural Information Processing Systems. 2017: 5967-5976.
Zhu J Y, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks [C]. Proceedings of the IEEE international conference on computer vision. 2017: 2223-2232.
Royer A, Bousmalis K, Gouws S, et al. Xgan: Unsupervised image-to-image translation for many-to-many mappings [J]. arXiv preprint arXiv: 1711.05139, 2017.
Anoosheh A, Agustsson E, Timofte R, et al. Combogan: Unrestrained scalability for image domain translation [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2018: 783-790.
Su J. O-GAN: Extremely Concise Approach for Auto- Encoding Generative Adversarial Networks [J]. arXiv preprint arXiv: 1903.01931, 2019.