Latent Variable Sampling
Truncation Trick
Introduced by Marchesi in Megapixel Size Image Creation using Generative Adversarial NetworksThe Truncation Trick is a latent sampling procedure for generative adversarial networks, where we sample $z$ from a truncated normal (where values which fall outside a range are resampled to fall inside that range). The original implementation was in Megapixel Size Image Creation with GAN. In BigGAN, the authors find this provides a boost to the Inception Score and FID.
Source: Megapixel Size Image Creation using Generative Adversarial Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Generation | 35 | 33.65% |
| Conditional Image Generation | 14 | 13.46% |
| Super-Resolution | 5 | 4.81% |
| Image Super-Resolution | 3 | 2.88% |
| Image-to-Image Translation | 3 | 2.88% |
| Bias Detection | 2 | 1.92% |
| Colorization | 2 | 1.92% |
| Image Restoration | 2 | 1.92% |
| Model Compression | 2 | 1.92% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
