🏛️Contrastive Language-Image Pre-Training (CLIP)
Also known as CLIP, OpenAI CLIP
An OpenAI model. It finds the words that best fit a picture.
Think of it like
It is like a game. You match each photo to the right label.
Example
Emma has 5,000 photos with no names. She asks CLIP to find 'a dog on a beach', and it ranks the photos that fit best.
Why it matters
It taught models to understand pictures through plain words. Photo search and many picture makers use ideas from it.
Definition
Common mistake
Key takeaways
- 1Pictures and words. Placed in one shared space.
- 2Pick the match. It scores each caption.
- 3No retraining. It works on new labels.