Truncation Trick

Introduced by Marchesi in Megapixel Size Image Creation using Generative Adversarial Networks

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 Networks

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Image Generation	39	16.81%
Conditional Image Generation	15	6.47%
Reinforcement Learning	7	3.02%
Multi-agent Reinforcement Learning	7	3.02%
Super-Resolution	6	2.59%
Reinforcement Learning (RL)	6	2.59%
Decision Making	5	2.16%
Denoising	4	1.72%
Diversity	4	1.72%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Latent Variable Sampling