While calculating AUC , the abnormal pixel are filtered with mask value of 0 , while in the agrivision data the anomaly pixels are masked with value of 1, am I missing something

Jingtao-Li-CVer / ASD

This is an official implementation for "Anomaly Segmentation for High-Resolution Remote Sensing Images Based on Pixel Descriptors“

MIT License

121 stars 0 forks source link

While calculating AUC , the abnormal pixel are filtered with mask value of 0 , while in the agrivision data the anomaly pixels are masked with value of 1, am I missing something #1

Open sambalshikhar opened 8 months ago

sambalshikhar commented 8 months ago

https://github.com/Jingtao-Li-CVer/ASD/blob/a00d10fff3bd1ad5b4a1dca7e5745bee1c098b3e/metrics/auroc.py#L38

Jingtao-Li-CVer commented 6 months ago

Sorry for the late reply. It is indeed a little confusing. I check the code and the anomaly pixels in agrivision data are actually masked with 0. I am pleased to discuss it with you further about this problem