A GAN, or Generative Adversarial Network, is a generative model that simultaneously trains two models: a generative model $G$ that captures the data distribution, and a discriminative model $D$ that estimates the probability that a sample came from the training data rather than $G$.
The training procedure for $G$ is to maximize the probability of $D$ making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions $G$ and $D$, a unique solution exists, with $G$ recovering the training data distribution and $D$ equal to $\frac{1}{2}$ everywhere. In the case where $G$ and $D$ are defined by multilayer perceptrons, the entire system can be trained with backpropagation.
(Image Source: here)
Source: Generative Adversarial NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Generation | 91 | 12.21% |
Translation | 36 | 4.83% |
Image-to-Image Translation | 33 | 4.43% |
General Classification | 24 | 3.22% |
Super-Resolution | 19 | 2.55% |
Semantic Segmentation | 16 | 2.15% |
Conditional Image Generation | 13 | 1.74% |
Image Super-Resolution | 12 | 1.61% |
Face Generation | 12 | 1.61% |