Figure 2 - Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning

The overview of our approach for cross-domain PAD. Our approach consists of a disentangled representation learning module (DR-Net) and a multi-domain feature learning module (MD-Net). With the face images from different domains as inputs, DR-Net can learn a pair of encoders for disentangled features for PAD and subject classification respectively. The disentangled features are fed to MD-Net to learn domain-independent representations for robust cross-domain PAD.

Go to figure page

Reference

Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning - Scientific Figure on ResearchGate. Available from: https://www.researchgate.net/figure/The-overview-of-our-approach-for-cross-domain-PAD-Our-approach-consists-of-a_fig1_340475151 [accessed 22 Apr 2025]

Caption

Figure 2. The overview of our approach for cross-domain PAD. Our approach consists of a disentangled representation learning module (DR-Net) and a multi-domain feature learning module (MD-Net). With the face images from different domains as inputs, DR-Net can learn a pair of encoders for disentangled features for PAD and subject classification respectively. The disentangled features are fed to MD-Net to learn domain-independent representations for robust cross-domain PAD.

Embed code

<a href="https://www.researchgate.net/figure/The-overview-of-our-approach-for-cross-domain-PAD-Our-approach-consists-of-a_fig1_340475151"><img src="https://www.researchgate.net/profile/Guoqing-Wang-9/publication/340475151/figure/fig1/AS:877527740452869@1586230325452/The-overview-of-our-approach-for-cross-domain-PAD-Our-approach-consists-of-a.jpg" alt="The overview of our approach for cross-domain PAD. Our approach consists of a disentangled representation learning module (DR-Net) and a multi-domain feature learning module (MD-Net). With the face images from different domains as inputs, DR-Net can learn a pair of encoders for disentangled features for PAD and subject classification respectively. The disentangled features are fed to MD-Net to learn domain-independent representations for robust cross-domain PAD."/></a>