How does the landmark augmentation code improve model performance?

[WangLedi]

Thanks for the great work, I have some questions about "exist_bi", the AUC on CDF before using the landmark augmentation code was 82%, but after using the landmark augmentation code the performance improved by almost ten percent, but I found that training the model Only used logging.disable(logging.FATAL) in sbi.py
mask = random_get_hull(landmark, img)[:, :, 0] #This function is not in the landmark enhancement code
logging.disable(logging.NOTSET), so how does exist_bi affect model performance?