How to calculate the mean IU score in image segmentation?

computer-vision image-segmentation evaluation-strategy

hkcqr · Jul 27, 2015 · Viewed 29.8k times · Source

How to compute the mean IU (mean Intersection over Union) score as in this paper?

Long, Jonathan, Evan Shelhamer, and Trevor Darrell. "Fully Convolutional Networks for Semantic Segmentation."

Answer

For each class Intersection over Union (IU) score is:

true positive / (true positive + false positive + false negative)

The mean IU is simply the average over all classes.

Regarding the notation in the paper:

n_cl : the number of classes
t_i : the total number of pixels in class i
n_ij : the number of pixels of class i predicted to belong to class j. So for class i:
- n_ii : the number of correctly classified pixels (true positives)
- n_ij : the number of pixels wrongly classified (false positives)
- n_ji : the number of pixels wrongly not classifed (false negatives)

You can find the matlab code to compute this directly in the Pascak DevKit here