search

unibas-gravis / Occlusion-Robust-MoFA

Other
207 stars 30 forks source link

problem during training Step4 ? #16

Closed DougDong666 closed 1 year ago

DougDong666 commented 1 year ago 
    > I was also troubled by this problem or bug. Have you solved this problem during training Step4 ?

Yes, I've solved. You should compare the code in the step4 with the code in the step1 and step3, and then fix it.

Originally posted by @NewtOliver in https://github.com/unibas-gravis/Occlusion-Robust-MoFA/issues/14#issuecomment-1329126412

DougDong666 commented 1 year ago

Loss functions in step4 are followed by article. But the loss function in step3 is a classic segmentation loss function. If the loss functions are changed by step3, I don not know why the article needs to mention its own loss fuctions.

ChunLLee commented 1 year ago

Hi, step 3 intends to pre-train the segmentation network with the preliminary segmentation masks estimated by our occlusion-robust function, not the ground truth masks. The losses in step 4 aim to improve the estimation in an unsupervised way.