AI engineering glossary · Computer vision
What is max pooling?
Max pooling: A pooling method that outputs the largest value inside each window of a feature map. It keeps the strongest detection of a pattern while discarding its exact position, giving mild translation invariance.
Max pooling: an example
For the 2 x 2 block [[1, 3], [2, 9]], max pooling outputs 9.
Related terms
More Computer vision terms
- Median filter
- Mixup
- MobileNet
- Morphological operations
- Non-maximum suppression
- Object detection
- OpenCV
- Optical character recognition
Where you learn it
Max pooling is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.