Corpus ID: 237532360

Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detection

  title={Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detection},
  author={Meiling Fang and Naser Damer and Florian Kirchbuchner and Arjan Kuijper},
With the increased deployment of face recognition systems in our daily lives, face presentation attack detection (PAD) is attracting much attention and playing a key role in securing face recognition systems. Despite the great performance achieved by the hand-crafted and deep-learningbased methods in intra-dataset evaluations, the performance drops when dealing with unseen scenarios. In this work, we propose a dual-stream convolution neural networks (CNNs) framework. One stream adapts four… Expand

Figures and Tables from this paper

Partial Attack Supervision and Regional Weighted Inference for Masked Face Presentation Attack Detection
The proposed method outperforms established PAD methods in the CRMA database by reducing the mentioned shortcomings when facing masked faces and presents a detailed step-wise ablation study pointing out the individual and joint benefits of the proposed concepts on the overall PAD performance. Expand


NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing
This work proposes the first FAS method based on neural architecture search (NAS), called NAS-FAS, to discover the well-suited task-aware networks, and develops a novel search space consisting of central difference convolution and pooling operators. Expand
Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues
This work proposes a novel Frequency in Face Forgery Network (F3-Net), taking advantages of two different but complementary frequency-aware clues, and applies DCT as the applied frequency-domain transformation to introduce frequency into the face forgery detection. Expand
Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection
A Convolutional Neural Network (CNN) based framework for presentation attack detection, with deep pixel-wise supervision, suitable for deployment in smart devices with minimal computational and time overhead is introduced. Expand
CBAM: convolutional block attention module. In Computer Vision - 15 th ECCV 2018
  • Proceedings, Part VII,
  • 2018
OULU-NPU: A Mobile Face Presentation Attack Database with Real-World Variations
This work introduces a new public face PAD database, OULU-NPU, aiming at evaluating the generalization of PAD methods in more realistic mobile authentication scenarios across three covariates: unknown environmental conditions, acquisition devices and presentation attack instruments. Expand
Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing
  • Suman Saha, Wenhao Xu, +4 authors L. Gool
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2020
This paper proposes a class-conditional domain discriminator module, that, coupled with a gradient reversal layer, tries to generate live and spoof features that are discriminative, but at the same time robust against the aforementioned variability factors. Expand
Regularized Fine-grained Meta Face Anti-spoofing
This work casts face anti-spoofing as a domain generalization (DG) problem, and attempts to address this problem by developing a new meta-learning framework called Regularized Fine-grained Meta-learning, which incorporates the domain knowledge of faceAnti-sp spoofing as the regularization so that meta- learning is conducted in the feature space regularized by the supervision of domain knowledge. Expand
Searching Central Difference Convolutional Networks for Face Anti-Spoofing
A novel frame level FAS method based on Central Difference Convolution (CDC), which is able to capture intrinsic detailed patterns via aggregating both intensity and gradient information is proposed. Expand
A competition on generalized software-based face presentation attack detection in mobile scenarios
This competition is to evaluate and compare the generalization performances of mobile face PAD techniques under some real-world variations, including unseen input sensors, presentation attack instruments (PAI) and illumination conditions, on a larger scale OULU-NPU dataset using its standard evaluation protocols and metrics. Expand
A face antispoofing database with diverse attacks
A face antispoofing database which covers a diverse range of potential attack variations, and a baseline algorithm is given for comparison, which explores the high frequency information in the facial region to determine the liveness. Expand