You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello. Could you please explain the NLL loss in modeling the uncertainty. It seems that when the difference between depth gt and depth prediction is large, larger U(D) will make the loss smaller. However, U(D) actually represents confidence in (4).
The text was updated successfully, but these errors were encountered:
Hello. Could you please explain the NLL loss in modeling the uncertainty. It seems that when the difference between depth gt and depth prediction is large, larger U(D) will make the loss smaller. However, U(D) actually represents confidence in (4).
The text was updated successfully, but these errors were encountered: