Discriminative model: The conditional probability of class label on data (posterior) $p(C_k\mid x)$ …

Contrastive models learn to compare1. Contrastive use special objective functions such as NCE Noise …

The task of GAN is to generate features $X$ from some noise $\xi$ and class labels $Y$, $$\xi, Y \to …

In contrastive methods, we can manipulate the data to create data entries and infer the changes …

The essence of GAN GAN The task of GAN is to generate features $X$ from some noise $\xi$ and class …

The likelihood is modeled as $$ \begin{align} p_\theta (x) &= \Pi_{t=1}^T p_\theta (x_t \mid …

It was discovered that the success of mutual information based contrastive learning Contrastive …

For a probability density $p(x)$ and a transformation of coordinate $x=g(z)$ or $z=f(x)$, the …

The simplest auto-encoder is rather simple. The loss can be chosen based on the demand, e.g., cross …

Variational Auto-Encoder (VAE) is very different from Generative Model: Auto-Encoder Generative …

Generative self-supervised learning models can utilize more data

Contrastive self-supervised learning models can utilize more data

Adversarial models use a generator and discriminator

Review of self-supervised learning.