Closed DougDong666 closed 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.
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.
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