Sign inSign in
ConceptAI & ML

Hard Negatives in vision-language models

Hard negatives are image or caption counterparts that differ by a minimal change, testing a model's ability to capture subtle compositional differences.
as Aishwarya Agrawal defines itUniversity of Montreal, Mila
Watch it explained

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.

CLIP1Vision-language models1

Lecturers

1

    Connections

    2

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

    Concept1

    Lecture1

    1 lecturer. 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.