AI engineering glossary · Computer vision
What is confidence score?
Confidence score: A number between 0 and 1 attached to a prediction, showing how strongly the model believes it. Detections below a chosen threshold are discarded, so the threshold trades missed objects against false alarms.
Confidence score: an example
With a threshold of 0.5, a detection scored 0.42 is dropped and one scored 0.87 is kept.
Related terms
More Computer vision terms
- Connectionist temporal classification
- Contour detection
- Contrastive language-image pretraining
- Contrastive learning
- Convolution
- Convolutional neural network
- Cross-correlation
- CutMix
Where you learn it
Confidence score is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.