zerooooone

Thanks for your great work! I have a question about selecting tokens with maximum activation in Part Selection Module. In Eq.6, is a_l^i the attention-score calculated separately for the class...

KL-loss is too large

3

Thanks for your great work! I noticed the KL-loss in your log is about 4. But when I run this code, the KL-loss was too large and turned out to...

The preprocessed FERPlus

1

Thanks for your great work! I run this model on RAF-DB you provided and got 90.8% accuracy. But only 85.5% accuracy was obtained on the official FERPlus dataset. I wonder...