Single-Side Domain Generalization for Face Anti-Spoofing

By Yunpei Jia, Jie Zhang, Shiguang Shan, Xilin Chen. Computer Vision and Pattern Recognition, 2020

303 citations recorded by the source corpus.

Existing domain generalization methods for face anti-spoofing endeavor to extract common differentiation features to improve the generalization. However, due to large distribution discrepancies among fake faces of different domains, it is difficult to seek a compact and generalized feature space for the fake faces. In this work, we propose an end-to-end single-side domain generalization framework (SSDG) to improve the generalization ability of face anti-spoofing. The main idea is to learn a generalized feature space, where the feature distribution of the real faces is compact while that of the fake ones is dispersed among domains but compact within each domain. Specifically, a feature generator is trained to make only the real faces from different domains undistinguishable, but not for the fake ones, thus forming a single-side adversarial learning. Moreover, an asymmetric triplet loss is designed to constrain the fake faces of different domains separated while the real ones aggregated. The above two points are integrated into a unified framework in an end-to-end training manner, resulting in a more generalized class boundary, especially good for samples from novel domains. Feature and weight normalization is incorporated to further improve the generalization ability. Extensive experiments show that our proposed approach is effective and outperforms the state-of-the-art methods on four public databases. The code is released online.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/c40a4a61e82433b62e599ba86b83c04d864e13fb

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

In Signal Processing

Citations in the corpus

Towards Out-Of-Distribution Generalization: A Survey (2021, unknown): “…3.2 ) [34], [35], [36](Section 3.2) SupervisedLearningModels ( Section 4 ) ( Section 4.1 ) [7], [8], [9], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49] [37], [39], [50], [51], [51], [52], [53], [53], [54], [54], [55], [56], [57], [58], [59], [60] [6], [61],…”
Face Anti-Spoofing with Human Material Perception (2020, background): “In order to learn generalized features for unseen attacks and environment, few-shot learning [8], zero-shot learning [8,29] and domain generalization [30,31,32] are introduced for FAS task.”
Domain Generalization: A Survey (2021, background): “Specifically, episodes construction concerns how each episode should be constructed using available samples, while meta-representation answers the question of what to meta-learn.”
Generalizing to Unseen Domains: A Survey on Domain Generalization (2021, methodology): “Domain adversarial learning: DANN [91, 92]/ MMD-AAE [72]/ DLOW [93]/ CIAN [94]/ ER [96]/ MADDG [95]/ FSUS [45]/ MMLD [97]/ DANNCE [98]/ CAADG [99]/ SSDG [100]/ AdaRNN [79] ASR-Norm [81]/ SADG [101]/ [102, 103]”