Setting of the fraction of the training labels

[gbliao]

Could you kindly share the setting used to finetune object detection models with a fraction of the training labels, e.g., 1%, 5%, or 10% on the Nuscenes dataset? It'll help me a lot.

[CSautier]

Hi, sorry for the delay.

I think there is a confusion here as we did not finetune object detection on nuScenes. We finetuned semantic segmentation on both nuScenes and SemanticKITTI, and object detection on KITTI only.

[gbliao]

Thanks for your reply.