Zhuoxiao (Ivan) Chen

Related Area: 3D Object Detection, Domain Adaptation Paper title: Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling Paper link: https://arxiv.org/abs/2307.07944 Code link: https://github.com/zhuoxiao-chen/ReDB-DA-3Ddet Thank you very much!

Hi, you can switch the branch to get the full code of OWAL. https://github.com/Luoyadan/CRB-active-3Ddet/tree/Open-CRB We will eventually merge them together in future work.

Hi, our framework currently supports two 3D detection models: PV-RCNN and SECONDIoU. To run Point-RCNN, you need to add some code that passes some key-value pairs in the data_dict that...

Yes, because our stage 2 requires dropout to get hypothesis labels. You may simply add a dropout layer to make it work.

Have you fixed this issue?

Hi, You can try this config file but you have to carefully modify some code in the **detectors/models** to pass the required variables to **queried strategies**. Also, we use secondiou...