Skip Connection Blocks
SRGAN Residual Block
Introduced by Ledig et al. in Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial NetworkSRGAN Residual Block is a residual block used in the SRGAN generator for image super-resolution. It is similar to standard residual blocks, although it uses a PReLU activation function to help training (preventing sparse gradients during GAN training).
Source: Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Super-Resolution | 28 | 39.44% |
| Image Super-Resolution | 17 | 23.94% |
| Quantization | 2 | 2.82% |
| Data Compression | 1 | 1.41% |
| Image Compression | 1 | 1.41% |
| Domain Adaptation | 1 | 1.41% |
| Infrared image super-resolution | 1 | 1.41% |
| Denoising | 1 | 1.41% |
| Image Generation | 1 | 1.41% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Batch Normalization
|
Normalization | |
Convolution
|
Convolutions | |
PReLU
|
Activation Functions | |
Residual Block
|
Skip Connection Blocks |
