search

lvwj19 / PPR-Net-plus

PPR-Net++: Accurate 6D Pose Estimation in Stacked Scenarios
Apache License 2.0
36 stars 6 forks source link

About classification_loss? #7

Closed hongzhidu closed 2 years ago

hongzhidu commented 2 years ago

Hi, Thanks for your excellent work!

May I consult you about why use cross entropy as the loss of semantic segmentation? If the label of each object is not fixed during training, will this loss function be invalid？

lvwj19 commented 2 years ago

In our experiments, the semantic id for each object was fixed during training, i.e., the objects of the same class had the same semantic id. I am curious, in which case that the semantic label of the object would be not fixed during training.

hongzhidu commented 2 years ago

Thanks for your reply! I just think the semantic id is unnecessary in this task. It might be more appropriate to do instance segmentation.

lvwj19 commented 2 years ago

In fact, semantic labels are common in these tasks, such as semantic segmentation for background and foreground point clouds in the stacked scene.

hongzhidu commented 2 years ago

Thanks again for your reply!