The 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 NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Generation | 38 | 19.39% |
Conditional Image Generation | 15 | 7.65% |
Multi-agent Reinforcement Learning | 7 | 3.57% |
Super-Resolution | 6 | 3.06% |
Reinforcement Learning (RL) | 6 | 3.06% |
Decision Making | 5 | 2.55% |
Denoising | 4 | 2.04% |
Clustering | 4 | 2.04% |
Benchmarking | 3 | 1.53% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |