Glossary term
Glossary term
Multimodal AI
In an image classification problem, an algorithm's ability to successfully classify images even when the position of objects within the image changes. For example, the algorithm can still identify a dog, whether it is in the center of the frame or at the left end of the frame.
See also size invariance and rotational invariance.
Created for this library
A computer vision team relies on translational invariance from its CNN so detection works regardless of object position in the image.
An autonomous-driving team relies on translational invariance so its detector works regardless of where objects appear in the frame.
A retail analytics team relies on translational invariance for shelf-image detection so products are recognized wherever they sit on the shelf.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License