search

meng-tang / rloss

Regularized Losses (rloss) for Weakly-supervised CNN Segmentation
MIT License
207 stars 47 forks source link

Gradient of the DenseCRF loss #3

Closed XiaoyanLi1 closed 5 years ago

XiaoyanLi1 commented 5 years ago

Hi, I'm very interested at your work and want to follow your paper in ECCV2018. I notice that in the paper the DenseCRF loss is image, while in the code it is image In both the code and the paper, its loss is computed as image. However, I think the gradient should be image image. Why is there a difference between the implementation and the theory? Should the first term of the gradient be ignored?

Heyi007 commented 5 years ago

same doubt, do you figure it out ?

meng-tang commented 5 years ago

When summing over k for the first term, it becomes a constant no matter whether S is discrete or continuous. So I chose to ignore the first term.

Tord-Zhang commented 4 years ago

@meng-tang Hi, I get confused. Since W is generated using Gaussian kernel, so every item in W is positive. S_k is the softmax output, so S_k is also positive. Then the gradient is always negative? So how can the gradient descent work?

Tord-Zhang commented 4 years ago

The loss just keep increasing......