AI engineering glossary · Computer vision
What is translation invariance?
Translation invariance: The property that a system gives the same answer when an object moves to a different position in the image. Convolution shares weights and pooling discards exact position, so CNNs are approximately, not perfectly, invariant to shifts.
Translation invariance: an example
A classifier should still say 'cat' whether the cat sits in the left or right half of the photo.
Related terms
- Max pooling
- Convolution
- Data augmentation
More Computer vision terms
Where you learn it
Translation invariance is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.