Skip to content

Multimodal AI

Image classification

Assigning a label or set of labels to an image as a whole.

Example

AI labels a photo as showing a bicycle.

Why people use it

It helps organize large image collections by what they appear to contain.

What you'll hear

“Sort these pictures by their main subject.”

What this means for you

Decide whether you need a whole-picture label or the object's exact location.

Can you control it?

Developer-only

The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.

Common questions

Does classification show where the bicycle is?
Not necessarily. Locating objects is a separate detection task.
Can the background affect the label?
Yes. The AI may rely on scenery or other clues instead of the object that matters.
Can one image have multiple labels?
Yes, if the system allows it. A photograph might show both a person and a bicycle.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice