Why result in CodaLab competitions is different from result in the paper？
Opened this issue · 1 comments
91916117qq commented
Dear author:
I am a novice in the field of 3d semantic segmentation. I notice your miou in CodaLab competitions is 68.9, but in your paper the result is 67.8. Why are the two results different? Thanks.
L-Reichardt commented
The SemanticKITTI benchmark lists 67.8
As a sidenode, this repository covers the implementation of C3D without the 2nd stage of the pointwise refinement module, or the weighted Cross entropy loss. The applicable mIOU to reference to is 64.3 from the authors other paper