Deep Tree Learning for Zero-Shot Face Anti-Spoofing

By Yaojie Liu, Joel Stehouwer, Amin Jourabloo, Xiaoming Liu. 2019

263 citations recorded by the source corpus.

Face anti-spoofing is designed to keep face recognition systems from recognizing fake faces as the genuine users. While advanced face anti-spoofing methods are developed, new types of spoof attacks are also being created and becoming a threat to all existing systems. We define the detection of unknown spoof attacks as Zero-Shot Face Anti-spoofing (ZSFA). Previous works of ZSFA only study 1-2 types of spoof attacks, such as print/replay attacks, which limits the insight of this problem. In this work, we expand the ZSFA problem to a wide range of 13 types of spoof attacks, including print attack, replay attack, 3D mask attacks, and so on. A novel Deep Tree Network (DTN) is proposed to tackle the ZSFA. The tree is learned to partition the spoof samples into semantic sub-groups in an unsupervised fashion. When a data sample arrives, being know or unknown attacks, DTN routes it to the most similar spoof cluster, and make the binary decision. In addition, to enable the study of ZSFA, we introduce the first face anti-spoofing database that contains diverse types of spoof attacks. Experiments show that our proposed method achieves the state of the art on multiple testing protocols of ZSFA.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Xiaoming Liu
2. Xilin Chen
3. Xiaogang Wang
4. Shiguang Shan
5. Luc Van Gool
6. Dacheng Tao
7. Guoying Zhao
8. Junjie Yan

In Information Systems

1. Xiaoming Liu
2. Guoying Zhao
3. Zitong Yu
4. Hu Han
5. Xiaobai Li
6. Shiguang Shan
7. Xilin Chen
8. Mohammad Rostami

In Signal Processing

1. Xiaoming Liu
2. Xilin Chen
3. Shiguang Shan
4. Hu Han
5. Zitong Yu
6. Guoying Zhao
7. Xiaobai Li
8. Joel Stehouwer

Citations in the corpus

• Detection and Continual Learning of Novel Face Presentation Attacks (2021, methodology): “3The Wild with Multiple Attacks Database (SiW-M) face anti-spoofing dataset [13] is another existing dataset with various PA types.”
• CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations (2020, methodology): “Third, SiW-M [24] is mainly used for Zero-Shot face antispoofing tasks.”
• Face Anti-Spoofing with Human Material Perception (2020, methodology): “Moreover, we also conduct cross-type testing on the lat-est SiW-M [29] dataset.”
• On the Detection of Digital Face Manipulation (2019, background): “i) Physical spoofing attacks can be as simple as face printed on a paper, replaying image/video on a phone, or as complicated as a 3D mask [8, 24, 34, 35].”
• Searching Central Difference Convolutional Networks for Face Anti-Spoofing (2020, methodology): “SiW-M is designed for cross-type testing for unseen attacks as there are rich (13) Performance Metrics.”
• Single-Side Domain Generalization for Face Anti-Spoofing (2020, methodology): “Both the domain adaptation methods [19, 36, 38] and zero-shot face anti-spoofing methods [24, 30] aim to improve the generalization ability.”
• Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation Learning (2020, background): “Liu et. al [31] defined the detection of unknown spoof attacks as ZSFA and proposed a novel deep tree network to partition the spoof samples into semantic sub-groups in an unsupervised fashion.”