Regarding the Lovasz Hinge loss
lmanan opened this issue · 3 comments
Hello,
I have more of a question here rather than an issue. I was curious about this line of code. As I understand, dist
is a variable that lies between 0 (pixel embedding is very far from the instance center) and 1 (pixel embedding lies atop the instance center). Also by that logic,
0< dist*2 -1 <1
Could you share any intuition on why this dist*2-1
is preferred instead of just using dist
, as the first argument to the lovasz hinge
class? Does it have better convergence properties for the loss in your opinion, for example? Thank you!
Hi,
@MLbyML I just wanted to share my thoughts with you since I stumbled about the same problem.
The signature of the loss function is lovasz_hinge(logits, labels, per_image=True, ignore=None)
- so it expects logits in the range of [-\infty. +\infty] instead of probabilities [0, 1].
By computing dist*2 -1
the author maps all predicted probabilities from [0,1] to [-1,1] to transform them to valid logits.
So from my point of view this mapping is necessary due to the signature of the loss function.
Indeed, I map the distance/probability to the interval [-1,1], as expected by the lovasz loss.
Thanks for the reply @JaWeyl and @davyneven That was helpful!