Generalizable Method for Face Anti-Spoofing with Semi-Supervised Learning
This addresses the need for reliable biometric authentication in commercial hardware, though it is incremental as it builds on existing CNN-based methods.
The paper tackles the problem of poor generalization in face anti-spoofing methods by proposing a semi-supervised learning approach, achieving state-of-the-art results on cross-dataset testing across MSU-MFSD, Replay-Attack, and OULU-NPU datasets.
Face anti-spoofing has drawn a lot of attention due to the high security requirements in biometric authentication systems. Bringing face biometric to commercial hardware became mostly dependent on developing reliable methods for detecting fake login sessions without specialized sensors. Current CNN-based method perform well on the domains they were trained for, but often show poor generalization on previously unseen datasets. In this paper we describe a method for utilizing unsupervised pretraining for improving performance across multiple datasets without any adaptation, introduce the Entry Antispoofing Dataset for supervised fine-tuning, and propose a multi-class auxiliary classification layer for augmenting the binary classification task of detecting spoofing attempts with explicit interpretable signals. We demonstrate the efficiency of our model by achieving state-of-the-art results on cross-dataset testing on MSU-MFSD, Replay-Attack, and OULU-NPU datasets.