Contrastive Loss

• This is the first loss used for Contrastive Learning
• Only one pair of data points are given
  • The points are similar or different

[!def] Contrastive Loss Formula
$$
Loss = (1-Y) * |x_i - x_j|^2 + Y * max(0, m - |x_i - x_j|^2)
$$
Here,

• Y = 0 if sample is similar
• Y = 1 if sample is different
• m is a hyper-parameter

This loss mainly minimized the Euclidian Distance between similar points and increases the Euclidian Distance between different points till some limit m.