A Survey of Generative Adversarial Networks Based on Encoder-Decoder Model

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.