Unified unsupervised and semi-supervised domain adaptation network for cross-scenario face anti-spoofing

作者：

Highlights：

• We address the cross-scenario face ant-spoofing problem via domain adaptation.

• We take consideration of unsupervised and semi-supervised settings.

• Different distribution alignment operations are conducted for better generalization.

• Our method is competitive with state-of-the-art methods in face anti-spoofing.

摘要

•We address the cross-scenario face ant-spoofing problem via domain adaptation.•We take consideration of unsupervised and semi-supervised settings.•Different distribution alignment operations are conducted for better generalization.•Our method is competitive with state-of-the-art methods in face anti-spoofing.

论文关键词：Face anti-spoofing,Face presentation attack detection,Domain adaptation,Deep learning

论文评审过程：Received 9 June 2020, Revised 3 February 2021, Accepted 6 February 2021, Available online 12 February 2021, Version of Record 20 February 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107888