aleksandrpikul / deep-pix-bis-pad.pytorch

An unofficial implementation of the paper "Deep Pixel-Wise Binary Supervision for Face Presentation Attack Detection" in Pytorch

Deep Pixel-wise Binary Supervision for Face PAD in Pytorch

Data

You can use NUAA, Celeba. In my branch I use Celeba

Testing

Run notebook/CELEBA-CELEBA in jupyter notebook for your database. You wil get metrics, ROC curve, confusion matrix.

Reference

[1] Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection
[2] https://gitlab.idiap.ch/bob/bob.paper.deep_pix_bis_pad.icb2019