LiWentomng / boxlevelset

The code for "Box-supervised Instance Segmentation with Level Set Evolution(ECCV2022)"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

No length regularization in LevelsetLoss?

Yangr116 opened this issue · comments

Hi, why is there not the third term (length regularization) in LevelsetLoss as described in Eq.3 of the paper? How many gains/drops will it bring?

@Yangr116
Hi, in the ablation study, the length regularization of Level set loss is adopted, which is beneficial for the performance (especially when the performance is low). In the main results, I found that the length regularization can bring the 0.2~0.4mAP drop. So, I commented the calculation for the better final results.

Thanks for your reply!