Contrastive Methods

Contrastive methods learn representations by contrasting positive and negative examples. This is one of methods used in Self-supervised Learning.

The goal is to learn an encoder $f$ such that:

$score (f (x), f (x^{+})) » score (f (x), f (x^{-}))$

where $x^{+}$ is a positive example, and $x^{-}$ is a negative example.