search

byungjae89 / SPADE-pytorch

PyTorch implementation of "Sub-Image Anomaly Detection with Deep Pyramid Correspondences"
Apache License 2.0
235 stars 43 forks source link

How about the PRO% #1

Open Whishing opened 4 years ago

Whishing commented 4 years ago

Do you find out how to achieve their PRO score？

JellyWong commented 3 years ago

Also expect the release of PRO calculation.

byungjae89 commented 3 years ago

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.

Classmate-Huang commented 3 years ago

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.

mgpadalkar commented 2 years ago

Seems to be implemented by @ssiing: https://github.com/ssiing/SAPDE