Robust3DOD icon indicating copy to clipboard operation
Robust3DOD copied to clipboard

Missing Balanced Adversarial Focal Training (BAFT) Implementation

Open miladabd opened this issue 1 year ago • 1 comments

Dear authors,

Thank you for sharing the official implementation of your work. I'm particularly interested in reproducing the adversarial training results using your Balanced Adversarial Focal Training (BAFT) approach.

I've noticed that the BAFT implementation seems to be missing from the current repository. Would it be possible to update the repo to include this?

Thank you for your time and consideration.

miladabd avatar Sep 02 '24 09:09 miladabd

The BAFT implementation for adversarial point perturbation is here: https://github.com/Eaphan/Robust3DOD/blob/main/tools/train_utils/train_utils_BAFT_perturbation_demo.py

Please change the hyper-parameters according to the type of detectors you use, such as "key" and "model_name". Then use the file to replace the origin "train_utils.py"

Eaphan avatar Sep 02 '24 12:09 Eaphan