zehuichen123/AutoAlignV2

Where do you implement Image Level Dropout?

Opened this issue · 1 comments

In your paper there is a section mentioned image level dropout which is very intuitive. However I didnt find how you implement it in your code. In your previous answer you said you found out only took 3 images as input can reach similar performance compared to 6 images input + image dropout.
Does this mean you chose to input 3 images directly?

I have the same question and want to know which piece of code implements this part of the logic.