Open Whishing opened 4 years ago
Also expect the release of PRO calculation.
PRO curve calculation is described in the paper:
They first separate anomaly masks into their connected components, therefore dividing them into individual anomaly regions. By changing the detection threshold, they scan over false positive rates (FPR), for each FPR they compute PRO i.e. the proportion of the pixels of each region that are detected as anomalous. The PRO score at this FPR is the average coverage across all regions. The PRO curve metric computes the integral across FPR rates from 0 to 0.3. The PRO score is the normalized value of this integral.
I would reproduce the PRO curve metric after finishing my busy works.
PRO curve calculation is described in the paper:
They first separate anomaly masks into their connected components, therefore dividing them into individual anomaly regions. By changing the detection threshold, they scan over false positive rates (FPR), for each FPR they compute PRO i.e. the proportion of the pixels of each region that are detected as anomalous. The PRO score at this FPR is the average coverage across all regions. The PRO curve metric computes the integral across FPR rates from 0 to 0.3. The PRO score is the normalized value of this integral.
I would reproduce the PRO curve metric after finishing my busy works.
Expect and Wait for your reproduction.
Seems to be implemented by @ssiing: https://github.com/ssiing/SAPDE
Do you find out how to achieve their PRO score?