search

Eli-YiLi / PMM

Pseudo-mask Matters in Weakly-supervised Semantic Segmentation
MIT License
44 stars 4 forks source link

Pretended Under-fitting Strategy #8

Closed Le312 closed 2 years ago

Le312 commented 2 years ago

Hello, I am recently reproducing your paper, where is the Pretended Under-fitting Strategy module reflected in the code? Thank you!

Eli-YiLi commented 2 years ago

It's in the segmentation part, in the phase of how to use pseudo-mask. Specifically, in the file of cross_entropy_loss.