Closed a18700 closed 4 years ago
I've experimented without label smoothing, and found out performance is hugely deterior to paper's. I think this should be clarified...
Maybe i think it's possible that performance of reported dgcnn is from effects of label smoothing, not a virtue of architectural innovations.
I've experimented without label smoothing, and found out performance is hugely deterior to paper's. I think this should be clarified...
Maybe i think it's possible that performance of reported dgcnn is from effects of label smoothing, not a virtue of architectural innovations.
Hi,
Are you running the pytorch code? I re-run the code without label smoothing and the result is very close.
While examining provided codes,
I found out label smoothing term is applied for cross entroy loss.
However, there is no description about that in the paper.
I doubt for the effects of this term.. Is there any official results without label smoothing term