Updating the generator in PPGN-h with gradients flowing through the encoder
arXiv:1804.00630
Abstract
The Generative Adversarial Network framework has shown success in implicitly modeling data distributions and is able to generate realistic samples. Its architecture is comprised of a generator, which produces fake data that superficially seem to belong to the real data distribution, and a discriminator which is to distinguish fake from genuine samples. The Noiseless Joint Plug & Play model offers an extension to the framework by simultaneously training autoencoders. This model uses a pre-trained encoder as a feature extractor, feeding the generator with global information. Using the Plug & Play network as baseline, we design a new model by adding discriminators to the Plug & Play architecture. These additional discriminators are trained to discern real and fake latent codes, which are the output of the encoder using genuine and generated inputs, respectively. We proceed to investigate whether this approach is viable. Experiments conducted for the MNIST manifold show that this indeed is the case.
arXiv commentMaster's thesis, 7 pages
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Generative Adversarial Text to Image Synthesis
- Improved Training of Wasserstein GANs
- A note on the evaluation of generative models
- Towards Principled Methods for Training Generative Adversarial Networks
- Synthesizing the preferred inputs for neurons in neural networks via deep generator networks
- A Note on the Inception Score
- Generating Images with Perceptual Similarity Metrics based on Deep Networks
- Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space
- Stacked Generative Adversarial Networks