Research map / Adversarial robustness and security / Attacks on text and graphs
Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use MADDG instead of the strongest reported baseline | Face anti-spoofing domain generalization · O&C&I to M | HTER (%): 22.72 -> 17.69 | Helped |
| Use MADDG instead of the strongest reported baseline | Face anti-spoofing domain generalization · O&M&I to C | HTER (%): 30.58 -> 24.5 | Helped |
| Use MADDG instead of the strongest reported baseline | Face anti-spoofing domain generalization · O&C&M to I | HTER (%): 29.14 -> 22.19 | Helped |
| Use MADDG instead of the strongest reported baseline | Face anti-spoofing domain generalization · I&C&M to O | HTER (%): 30.17 -> 27.98 | Helped |
| Add multi-adversarial domain generalization with multiple domain discriminators (ablation) | MADDG · O&C&I to M; O&M&I to C; O&C&M to I; I&C&M to O | HTER (%): 21.55 vs 17.69; 28.67 vs 24.5; 36.50 vs 22.19; 29.63 vs 27.98 | Helped |
| Add the dual-force triplet-mining constraint (ablation) | MADDG · O&C&I to M; O&M&I to C; O&C&M to I; I&C&M to O | HTER (%): 20.84 vs 17.69; 30.46 vs 24.5; 34.99 vs 22.19; 29.75 vs 27.98 | Helped |
| Add auxiliary face-depth supervision (ablation) | MADDG · O&C&I to M; O&M&I to C; O&C&M to I; I&C&M to O | HTER (%): 34.29 vs 17.69; 39.95 vs 24.5; 37.44 vs 22.19; 39.39 vs 27.98 | Helped |
| Use MADDG instead of MMD-AAE | Face anti-spoofing domain generalization · O&M&I to C | HTER (%): 44.59 -> 24.5 | Helped |
| Use MADDG instead of score-level or feature-level fusion | Face anti-spoofing domain generalization · O&M&I to C | HTER (%): 46.62; 52.32; 24.5 | Helped |
Closest papers by meaning
- Test-Time Domain Generalization for Face Anti-Spoofing (CVPR 2024 · similarity 0.89)
- Gradient Alignment for Cross-Domain Face Anti-Spoofing (CVPR 2024 · similarity 0.87)
- Multi-Domain Incremental Learning for Face Presentation Attack Detection (AAAI 2024 · similarity 0.87)
- Rethinking Generalizable Face Anti-spoofing via Hierarchical Prototype-guided Distribution Refinement in Hyperbolic Space (CVPR 2024 · similarity 0.87)
- CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing (CVPR 2024 · similarity 0.86)
- FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models (AAAI 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.