Latent Optimisation is a technique used for generative adversarial networks to refine the sample quality of $z$. Specifically, it exploits knowledge from the discriminator $D$ to refine the latent source $z$. Intuitively, the gradient $\nabla_{z}f\left(z\right) = \delta{f}\left(z\right)\delta{z}$ points in the direction that better satisfies the discriminator $D$, which implies better samples. Therefore, instead of using the randomly sampled $z \sim p\left(z\right)$, we uses the optimised latent:
$$ \Delta{z} = \alpha\frac{\delta{f}\left(z\right)}{\delta{z}} $$
$$ z' = z + \Delta{z} $$
Source: LOGAN .
Source:PAPER  DATE 

LOGAN: Latent Optimisation for Generative Adversarial Networks

20191202 
Deep Compressed Sensing

20190516 
TASK  PAPERS  SHARE 

Conditional Image Generation  1  33.33% 
Image Generation  1  33.33% 
MetaLearning  1  33.33% 
COMPONENT  TYPE 


🤖 No Components Found  You can add them if they exist; e.g. Mask RCNN uses RoIAlign 