Generalizable Method for Face Anti-Spoofing with Semi-Supervised Learning

13 Jun 2022  ·  Nikolay Sergievskiy, Roman Vlasov, Roman Trusov ·

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.

PDF Abstract

Results from the Paper

 Ranked #1 on Face Anti-Spoofing on Replay-Attack (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Face Anti-Spoofing MSU-MFSD Entry-V2 Equal Error Rate 0 # 1
HTER 0 # 1
Face Anti-Spoofing OULU-NPU Entry-V2 ACER 3.2 # 2
HTER 2.6 # 1
Face Anti-Spoofing Replay-Attack Entry-V2 EER 0 # 1
HTER 0 # 1


No methods listed for this paper. Add relevant methods here