search

yinjunbo / SSDA3D

Thie repo provides the official implementation of our AAAI-2023 paper “SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud”.
Apache License 2.0
44 stars 2 forks source link

ST3D-UDA and ST3D-SSDA Comparison #5

Closed c7huang closed 1 year ago

c7huang commented 1 year ago

Hi, thanks for sharing the code for your project!

In the paper there are comparisons with ST3D in both UDA and SSDA settings. I have a few questions about these experiments.

jetpackfirstme commented 1 year ago

Hi, thanks for sharing the code for your project!

In the paper there are comparisons with ST3D in both UDA and SSDA settings. I have a few questions about these experiments.

  • Since this repository does not seem to contain code related to ST3D, did you modify the official ST3D release to use CenterPoint?
  • For waymo->nuscenes experiments, the ST3D configuration has pseudo-label updates disabled (UPDATE_PSEUDO_LABEL_INTERVAL=1000), were you using the same settings as them?

Thanks for your attention. For the first question, the answer is yes. We conduct the experiments on CenterPoint using the same strategy as that in ST3D, and utilize more information compared with ST3D, e.g., point intensity and GT_SAMPLING. For the second question, the answer is also yes. In fact, we found that when adapting Waymo to nuScenes, it seems that ST3D didn't apply the newly proposed method in the paper. So we follow the official ST3D configurations. I hope this will help you.

c7huang commented 1 year ago

That makes sense. Thanks for the clarification!