Research map / Label-efficient and robust learning / Domain adaptation and generalization
Single-Side Domain Generalization for Face Anti-Spoofing
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 SSDG-R instead of MADDG | Face anti-spoofing domain generalization · Four cross-database testing tasks | HTER (%): 17.69 -> 7.38; 24.50 -> 10.44; 22.19 -> 11.71; 27.89 -> 15.61 | Helped |
| Use SSDG-R instead of MADDG | Face anti-spoofing domain generalization · Four cross-database testing tasks | AUC (%): 88.06 -> 97.17; 84.51 -> 95.94; 84.99 -> 96.59; 80.02 -> 91.54 | Helped |
| Add asymmetric triplet loss (ablation) | SSDG-M · Four cross-database testing tasks | HTER (%): 21.19 -> 16.67; 26.78 -> 23.11; 23.93 -> 18.21; 25.43 -> 25.17 | Helped |
| Add single-side adversarial learning (ablation) | SSDG-M · Four cross-database testing tasks | HTER (%): 24.05 -> 16.67; 28.11 -> 23.11; 21.29 -> 18.21; 26.62 -> 25.17 | Helped |
| Add feature and weight normalization (ablation) | SSDG-M · Four cross-database testing tasks | HTER (%): 17.86 -> 16.67; 30.11 -> 23.11; 25.57 -> 18.21; 29.74 -> 25.17 | Helped |
| Add asymmetric triplet loss (ablation) | SSDG-R · Four cross-database testing tasks | HTER (%): 8.81 -> 7.38; 14.33 -> 10.44; 15.21 -> 11.71; 21.98 -> 15.61 | Helped |
| Add single-side adversarial learning (ablation) | SSDG-R · Four cross-database testing tasks | HTER (%): 11.19 -> 7.38; 12.89 -> 10.44; 12.14 -> 11.71; 18.06 -> 15.61 | Helped |
| Add feature and weight normalization (ablation) | SSDG-R · Four cross-database testing tasks | HTER (%): 10.24 -> 7.38; 12.78 -> 10.44; 12.64 -> 11.71; 15.99 -> 15.61 | Helped |
| Use ResNet18-based architecture instead of MADDG-based architecture | SSDG feature generator · Four cross-database testing tasks, average | Avg HTER (%): 20.79 -> 11.29 | Helped |
Closest papers by meaning
- Gradient Alignment for Cross-Domain Face Anti-Spoofing (CVPR 2024 · similarity 0.92)
- Test-Time Domain Generalization for Face Anti-Spoofing (CVPR 2024 · similarity 0.92)
- CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing (CVPR 2024 · similarity 0.90)
- Rethinking Generalizable Face Anti-spoofing via Hierarchical Prototype-guided Distribution Refinement in Hyperbolic Space (CVPR 2024 · similarity 0.90)
- Domain-Hallucinated Updating for Multi-Domain Face Anti-spoofing (AAAI 2024 · similarity 0.88)
- SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining (AAAI 2025 · similarity 0.87)
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.