AI engineering glossary · Computer vision
What is dice coefficient?
Dice coefficient (also called Dice score, F1 score for segmentation): An overlap score for masks: Dice = 2 x |A and B| / (|A| + |B|), ranging from 0 to 1. It is common in medical segmentation, and 1 minus Dice is often used as a loss.
Dice coefficient: an example
If a predicted mask has 80 pixels, the true mask 100 and they share 70, Dice = 140 / 180 = 0.78.
Related terms
More Computer vision terms
- Dilated convolution
- Document layout analysis
- Edge detection
- EfficientNet
- Face detection
- Fast R-CNN
- Faster R-CNN
- Feature descriptor
Where you learn it
Dice coefficient is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.