Jaccard index - Intersection over Union - Jaccard similarity coefficient - IoU - 交并比 (六)

Jaccard index - Intersection over Union - Jaccardsimilarity coefficient - IoU - 交并比 (六)

The Jaccard index, also known asIntersection over Union and the Jaccard similarity coefficient (originallycoined coefficient de communauté by Paul Jaccard), is a statistic used forcomparing the similarity and diversity of sample sets. The Jaccard coefficientmeasures similarity between finite sample sets, and is defined as the size ofthe intersection divided by the size of the union of the sample sets:

(If A and B are both empty, we defineJ(A,B) = 1.)

The Jaccard distance, which measuresdissimilarity between sample sets, is complementary to the Jaccard coefficientand is obtained by subtracting the Jaccard coefficient from 1, or,equivalently, by dividing the difference of the sizes of the union and theintersection of two sets by the size of the union:

Tells you how well predicted box overlapsground truth box.

https://en.wikipedia.org/wiki/Jaccard_index