AI engineering glossary · Computer vision
What is zero-shot learning?
Zero-shot learning: Recognising classes the model was never explicitly trained on, usually by relating images to text descriptions. It avoids collecting labelled data for every new category. It relies on shared meaning, such as text embeddings, to bridge seen and unseen classes.
Zero-shot learning: an example
CLIP can label a photo as 'a kolam pattern' though no training step used that class name.
Related terms
More Computer vision terms
- 1x1 convolution
- Affine transformation of images
- AlexNet
- Anchor box
- Aspect ratio
- Average pooling
- Binary mask
- Bottleneck block
Where you learn it
Zero-shot learning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.