happyharrycn/actionformer_release

K-way Binary Classification vs. Multi-class Classification

Closed this issue · 2 comments

Thanks for your wonderful work! My question is that why you choose to treat a K-way classification as K binary classification for action label prediction. Is this an experimental result that binary focal loss outperforms CE loss, or there are some other motivation behind it?

With the label assignment strategy in ActionFormer, positive samples will be much smaller than positive samples, thus we choose K-way binary classification along with focal loss.

Thanks for your answer!