-
Notifications
You must be signed in to change notification settings - Fork 108
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Loss function: additional robustness? #19
Comments
Hi, @blukaz . We haven't tried it. |
I'll try it out and let you know. |
@ thank you for the link! Keep you updated in the coming days. |
@yuxumin do you have any recommendation on how to fix clustering of the coarse prediction? I have the problem that the dense loss is a magnitude lower than the coarse. Did you encounter similar problems? |
You mean that the CD-loss for dense cloud pairs are much less than those for coarse pairs? Yes, i notice it too. I find some works adopt the weighted sum of these two losses. For example, |
Yes, exactly that. Ok, I see. I'll try that. Thank you for your quick response! |
Hi @yuxumin, I've been wondering if you tried to combine both the CD_l1 & CD_l2 loss function during training? Maybe it would yield better results?
The text was updated successfully, but these errors were encountered: