How did you acquire patch-level labels when calculating patch loss?
Closed this issue · 1 comments
yuanpinz commented
Since only WSI-level labels were available.
YashSharma commented
Hey @yuanpinz, we assume patch-level labels to be the same as WSI-level labels (weak assumption). Mainly, we make this assumption to stabilize small data size training. You can train without patch-level labels also and evaluate the performance.