Generative Models
LSGAN
Introduced by Mao et al. in Least Squares Generative Adversarial NetworksLSGAN, or Least Squares GAN, is a type of generative adversarial network that adopts the least squares loss function for the discriminator. Minimizing the objective function of LSGAN yields minimizing the Pearson $\chi^{2}$ divergence. The objective function can be defined as:
$$ \min_{D}V_{LSGAN}\left(D\right) = \frac{1}{2}\mathbb{E}_{\mathbf{x} \sim p_{data}\left(\mathbf{x}\right)}\left[\left(D\left(\mathbf{x}\right) - b\right)^{2}\right] + \frac{1}{2}\mathbb{E}_{\mathbf{z}\sim p_{\mathbf{z}}\left(\mathbf{z}\right)}\left[\left(D\left(G\left(\mathbf{z}\right)\right) - a\right)^{2}\right] $$
$$ \min_{G}V_{LSGAN}\left(G\right) = \frac{1}{2}\mathbb{E}_{\mathbf{z} \sim p_{\mathbf{z}}\left(\mathbf{z}\right)}\left[\left(D\left(G\left(\mathbf{z}\right)\right) - c\right)^{2}\right] $$
where $a$ and $b$ are the labels for fake data and real data and $c$ denotes the value that $G$ wants $D$ to believe for fake data.
Source: Least Squares Generative Adversarial Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Face Generation | 3 | 11.54% |
| Image Generation | 3 | 11.54% |
| Image Enhancement | 1 | 3.85% |
| Image Segmentation | 1 | 3.85% |
| Low-Light Image Enhancement | 1 | 3.85% |
| Semantic Segmentation | 1 | 3.85% |
| Diversity | 1 | 3.85% |
| Dimensionality Reduction | 1 | 3.85% |
| Image-to-Image Translation | 1 | 3.85% |
Batch Normalization
Convolution
Dense Connections
GAN Least Squares Loss
Leaky ReLU
ReLU
