A neural network with twin branches sharing rules to compare two items.
It is like two identical bouncers at a school dance. Each checks one ID with the same rulebook. Then they compare notes and give one match score.
You meet it in face unlock. It also helps signature checks and image search. Its job is to judge if two things are alike.
Metric Learning
A Siamese Network is a common similarity model in Metric Learning.
Contrastive Learning
Contrastive Learning trains it with pairs, so matching items move closer.
Embedding
It turns both inputs into embeddings, then compares their distance.
Face Recognition
Face Recognition can use it to decide if two faces are the same person.