DUC_HDC performance

Question

DUC_HDC performance

InstantWindy opened this issue 6 years ago · comments

Hello! Do you use the 'DUC_HDC‘’ model train the Voc2012 dataset? I use it ,but I found the result was not good, it appears the griding situation,But it should not be the case, because the model is the solution to the grid phenomenon.I don't why ,could you help me? Thanks!

Saeed Izadi · Answer 1 · Tue May 08 2018 14:38:06 GMT+0800 (China Standard Time)

Hi,

Yes, I'm getting the grid-like pattern as well. The implementation is correct, and I'm skeptical to the theory behind the DUCHDC method.

InstantWindy · Answer 2 · Tue May 08 2018 16:08:22 GMT+0800 (China Standard Time)

Thanks! I have another question. If it is a binary classification, using BCELoss to calculate the loss, how do you calculate the accuracy and mean IoU? Is BCELoss good for image segmentation? I'm sorry to trouble you

Saeed Izadi · Answer 3 · Fri May 11 2018 08:41:30 GMT+0800 (China Standard Time)

BCE stands for binary cross entropy. So, it's suitable for binary segmentation task. The accuracy and IoU can be simply calculated for binary segmentation tasks. Just treat each pixel as a sample. Yes, BCE is good for binary segmentation.