Generative Adversarial Network (GAN)

GAN models are known for potentially unstable training and less diversity in generation due to their adversarial training nature.


VAE relies on a surrogate loss.

Flow-based Model

Flow models have to use specialized architectures to construct reversible transform.

Normalizing flows is a class of generative models focusing on mapping a complex probability distribution to a simple distribution such as a Gaussian.

Diffusion Model

overviews of different generative models


Conditional Generation

consider learning a conditional mapping function G:XYG: \mathcal X \rightarrow \mathcal Y which generates an output yY\mathbf y \in \mathcal Y. Our goal is to learn a multi-modal mapping G:X×ZYG: \mathcal X \times \mathcal Z \rightarrow \mathcal Y such that an input $x$ can be mapped to multiple and diverse ouputs in $\mathcal Y$ depending on the latent factors encoded in $\mathbf z \in \mathcal Z$.

offen suffers from mode-collapse problem.

results matching ""

    No results matching ""