You Only Look Once (YOLO)
Definition
YOLO detects object classes and their image positions in a single processing step.
A family of single-stage object detectors that predict classes and bounding boxes in a single forward pass.
Simply explained
The AI looks at an image and simultaneously marks which objects it recognizes and where they are located.
Why it matters in practice
The term helps to select, develop, evaluate AI systems in a well-founded manner and realistically assess their technical risks.
Example from business
A manufacturer detects components on the line and measures recall for small and occluded objects.
Limits and pitfalls
- YOLO is not a single immutable architecture; version names, license, latency, and accuracy must be specified concretely.
Origin & history
Redmon and co-authors published YOLO in 2015/2016; numerous independent successor variants followed.
Use in mid-sized companies
- Possible application: A manufacturer detects components on the line and measures recall for small and occluded objects.
Frequently asked questions
What does You Only Look Once (YOLO) mean?
A family of single-stage object detectors that predict classes and bounding boxes in a single forward pass. What should you watch out for? YOLO is not a single immutable architecture; version names, license, latency, and accuracy must be specified concretely.
Sources
- You Only Look Once · Redmon et al., You Only Look Once
Source checked on 10.10.2026. Editorial application examples are hypothetical; no evidence of real customer results.
Editorially reviewed on: