search

YudeWang / SEAM

Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation, CVPR 2020 (Oral)
MIT License
542 stars 97 forks source link

OHEM #26

Closed hchoi71 closed 3 years ago

hchoi71 commented 3 years ago

Hello, Yude.

Thanks for sharing this great work!

I have one question about table 1. You mentioned that you reported results in table 1 with the training set. Then, it seems OHEM process should be involved with train_SEAM.py. Is that correct? Does your repo include OHEM process? How can I use OHEM in your code?

Thanks

YudeWang commented 3 years ago

Hi @hchoi71 , OHEM means the topk selection here. https://github.com/YudeWang/SEAM/blob/c55601649c5fa676836d3ec70ec044541b7d1d83/train_SEAM.py#L137

hchoi71 commented 3 years ago

Oh I see. Thanks @YudeWang