search

xrli-U / MuSc

This is an official PyTorch implementation for "MuSc : Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images" (MuSc ICLR2024).
MIT License
207 stars 12 forks source link

about figure 2 visualization #11

Open zyz1002 opened 1 month ago

zyz1002 commented 1 month ago

Very good work!!! How is the heat map in the bottom right corner of Figure 2 visualized in the article? Can you explain or provide relevant code? Thank you!!

xrli-U commented 1 month ago

The bottom right corner of Figure 2 shows the anomaly map under the case of $r=5$. Specifically, this can be obtained by replacing $r∈{1,3,5}$ in formula (3) with $r∈{5}$. In our code, you only need to change the setting --r_list 5 in the scripts/musc.py file.

zyz1002 commented 1 month ago

thanks!!