Open whuhxb opened 2 years ago
Hi, Both feat_mlp and centers_logits are designed to boost representation learning, and the final prediction depends only on logits. I'm not familiar with 3D segmentation, but SCL is only used to help learn a more balanced feature space and help get better predictions, and it can be discarded during testing.
Hi @FlamieZhu
I‘m trying to apply the loss you proposed to 3D point cloud. I have one question. How to understand feat_mlp, logits, centers_logits in 2D image network? If I use this loss for 3D semantic segmentation, how to correspond them? Thanks a lot.
I have seen that you used CE+SCL in training, but in testing just used CE. Could I still use CE+SCL in testing?
Xiaobing
Hi, Is the 3D segmentation effect improved?
Hi @FlamieZhu I‘m trying to apply the loss you proposed to 3D point cloud. I have one question. How to understand feat_mlp, logits, centers_logits in 2D image network? If I use this loss for 3D semantic segmentation, how to correspond them? Thanks a lot. I have seen that you used CE+SCL in training, but in testing just used CE. Could I still use CE+SCL in testing? Xiaobing
Hi, Is the 3D segmentation effect improved?
Still trying.
Hi @FlamieZhu
I‘m trying to apply the loss you proposed to 3D point cloud. I have one question. How to understand feat_mlp, logits, centers_logits in 2D image network? If I use this loss for 3D semantic segmentation, how to correspond them? Thanks a lot.
I have seen that you used CE+SCL in training, but in testing just used CE. Could I still use CE+SCL in testing?
Xiaobing