training as multi-classification task, the result was poor.

[liangshi036]

Hi,

I prepare the data as describe in https://github.com/Davidzhangyuanhan/CelebA-Spoof which have 11 different spoof types, I crop the face using the BBox in the json files . then I training it just as multi-classification, having 11 classes. (NOT as multi-label task as you do.)

I try different SOTA nets, Efficientnet-V2, MobileNetV3, etc.

but strange enough, after 300 epochs , I got 92% top1 accuracy. is there anything wrong with it?

As binary classification, spoof or not , I got ACC1 98+, probabaly because of unbalanced data ? "live" class have much more images.

Have you examine the different spoof types's accuracy ?