In the YOLO9000 paper, they define the distance between a box and centroid as $d(box, centroid) = 1 - IOU(box, centroid)$. I think box here is a ground truth bounding box, but what is centroid?
Asked
Active
Viewed 29 times
1 Answers
3
The centroid is referring to the central point of a k-means cluster.
Where does k-means come in? At the end of p.2 they say:
Instead of choosing priors by hand, we run k-means clustering on the training set bounding boxes to automatically find good priors.
Also see Figure 2.

Darren Cook
- 1,772
- 1
- 12
- 26