Sign inSign in
ConceptAI & MLMedicine

CLIP

One word, taught differently in 2 fields. Each use is given apart.

In AI & ML

A model using contrastive objectives and language supervision to learn generalizable semantic concepts across images.
as Dorsa Sadigh defines itUC BerkeleyThe wording closest to all 3 definitions

In Medicine

A small peptide fragment remaining from the invariant chain docked into the MHC class II binding site after proteolytic cleavage.

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Contrastive learning1Embedding1Encoder1Endosome1Image and text encoders1Invariant chain1Language supervision1MHC class II1

Opens up

Concepts that name this one as a prerequisite.

In AI & ML

3

Each in their own terms, from the easiest level.

  • Sara Beery

    MIT · Undergraduate

    A model that tries to make descriptions and images that correspond to them close together in a joint embedding space.
  • Steven Feng

    Stanford University · Undergraduate

    A model that aligns text representations with image representations through separate encoders trained on paired data.
    • 47:57Overview of Transformers (Stanford CS25: Transformers United V6)

In Medicine

1

    Lectures that assume it

    3

    Connections

    15

    The lectures that define it or assume it, and the concepts next to it.

    4 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.