AI engineering glossary · Computer vision
What is CLIP (contrastive language-image pretraining)?
Contrastive language-image pretraining (also called CLIP): CLIP, a model trained on hundreds of millions of image-caption pairs to place matching images and texts near each other in a shared embedding space. It enables zero-shot classification by comparing an image with text prompts.
Contrastive language-image pretraining: an example
To classify a photo, compare it with the texts 'a photo of a dosa' and 'a photo of an idli' and pick the closer one.
Related terms
More Computer vision terms
- Contrastive learning
- Convolution
- Convolutional neural network
- Cross-correlation
- CutMix
- Cutout
- Data augmentation for images
- DeepLab
Where you learn it
Contrastive language-image pretraining is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.