These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.
The Dice score, also known as the Dice Similarity Coefficient, is a measure of the similarity between two sets of data, usually represented as binary arrays. In the context of image segmentation, for example, the Dice score can be used to evaluate the similarity between a predicted segmentation mask and the ground truth segmentation mask. The Dice score ranges from 0, indicating no overlap, to 1, indicating perfect overlap.
The Dice score is calculated as follows:
Dice score = 2 * (number of common elements) / (number of elements in set A + number of elements in set B)
In other words, the Dice score is equal to twice the size of the intersection divided by the sum of the sizes of the two sets. This means that the Dice score measures the proportion of overlap between the two sets, normalized by the size of the sets.
The Dice score supports Safety by providing a quantitative measure of output accuracy, which is critical in applications where incorrect outputs could cause harm (e.g., medical image segmentation). It also supports Robustness by enabling the assessment of model performance consistency across different datasets or under varying conditions, helping to identify potential failures or weaknesses. However, these connections are indirect and depend on the broader context of system deployment and evaluation.
About the metric
You can click on the links to see the associated metrics
Objective(s):
Purpose(s):
Lifecycle stage(s):
Target users:
