AI engineering glossary · Computer vision
What is pooling layer?
Pooling layer: A layer that shrinks a feature map by summarising each small window with one number, commonly the maximum or the average. It reduces computation, adds tolerance to small shifts of the object, and lets later layers see larger regions.
Pooling layer: an example
A 2 x 2 max pool with stride 2 turns a 56 x 56 feature map into 28 x 28, keeping the strongest value in each block.
Related terms
More Computer vision terms
- Precision and recall for detection
- Pretrained backbone
- R-CNN
- Random crop
- RANSAC
- Receptive field
- Region proposal
- Region proposal network
Where you learn it
Pooling layer is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.