Vision icons

The 7 vision icons, described

Agent imageagent-image

An agent beside a picture — a vision agent that looks at and understands images.

Face detectionface-detect

A face between the two corner brackets that found it — face detection and facial recognition.

Image captionimage-caption

A picture with the model's description written beneath it — image captioning and alt text.

Image segmentationimage-segment

The photo frame with a hill and a corner picked out — every pixel given to the thing it belongs to.

Object detectionobject-detect

A labelled bounding box drawn around the thing the model found — object detection in an image.

Vision encodervision-encoder

A picture beside a model core — the vision encoder that turns pixels into tokens.

Visual groundingvisual-grounding

A location pin dropped inside a picture — grounding words to the exact pixels they refer to.

In code, each is one import — import { AgentImage } from "@iconmind/react/icons/agent-image" — and the same name in Vue, Svelte, Solid, Preact, React Native, Astro, Blade and Flutter.

Tags these icons also carry