• References
  • https://handong1587.github.io/deep_learning/2015/10/09/genrative-models.html

Theoretical Issues

Generative Adversarial Networks

• Source code
  • https://github.com/goodfeli/adversarial
• Contribution Points
  • Induce the concept of Generative Adversarial Networks for replacing traditional Probabilistic Graphical Models
  • Prove the existence and the convergence of the solution of it's main objective function

Unsupervised Representation Learning With Deep Convolutional Generative Adversarial Networks

• Source code
  • https://github.com/Newmu
  • https://github.com/soumith/dcgan.torch
  • https://github.com/soumith/ganhacks
• Contribution Points
  • Make GAN stable to train in most settings
    • Replace any pooling layers with "Strided convolutions(discriminator) and fractional strided convolutions (generator).
    • Use batchnorm in both the generator and the discriminator except for the generator output layer and the discriminator input layer.
    • Remove fully onnected hidden layers for deeper architecture.
    • Use ReLU activation in generator for all layers except for the output, which uses "tanh".
    • Use LeakyReLU activation in discriminator for all layers.
    • Preprocess scaling training images to the range of [-1, 1] for "tanh"
  • Show the Generators have interesting vector arithmetic properties allowing for easy manipulation of many semantic qualities of generated samples

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

• Source code
  • https://github.com/openai/InfoGAN
    

Energy-based Generative Adversarial Networks

• Source code
  • Not support the author's official code
• Contribution Points
  • An Energy-based Formulation for generative adversarial training
  • A proof
  • A EBGAN framework with the discriminator using an auto-encoder architecture in which the energy is the reconstruction error.
  • A set of systematic experiments to explore the set of hyper-parameters and architectural choices that produce good results for EBGANs and conventional GANs.
    • EBGAN is more robust
    • EBGAN can generate reasonable-looking high-resolution images from 256x256 pixel resolution

SeqGAN

• Source code
  • https://github.com/LantaoYu/SeqGAN

Applications

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

• $\hat{x} = G(z)$
  • Z is Low Resolution Image, not noise vector Z
  • Output X is Super Resolution Image from G
• $D(x)$
  • X is Ground Truth High Resolution Images or Generated Super Resolution Images
• Upscaling using Sub pixel Convlutional Neural Network

  We increase the resolution of the input image with two trained sub-pixel convolution [ D. Rueckert, and Z. Wang. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. ]

Semantic Segmentation using Adversarial Network

• Set Segmentation Networks as Typical G(z)
• invent new network D(x) for matching function, If ground truth class map and segmentation map from G(z) is similar -> 1 otherwise 0
• New D(x)
  • Input: Target image to segment and Class map
    • ground truth or Segmented map from G(z) Here z is the target image, There is no noise Z

Generative Adversarial Text to Image Synthesis