Research map / Label-efficient and robust learning / Domain adaptation and generalization
Bottom-Up Domain Prompt Tuning for Generalized Face Anti-Spoofing
Siqi Liu, Qirui Wang, Pong C. Yuen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add recording domain generalization prompt learning to spoofing domain tuning (ablation) | BUDoPT · ICM->O | HTER: 3.51 -> 3.01 | Improved |
| add adversarial domain learning (ablation) | BUDoPT · ICM->O | HTER: 3.01 -> 2.50 | Improved |
| add context-aware domain clue (ablation) | BUDoPT · ICM->O | HTER: 2.50 -> 2.26 | Improved |
| use intuitive textual recording domain prompt instead of learned visual domain prompt (ablation) | BUDoPT · ICM->O | HTER: 3.51 -> 5.78 | Hurt |
| use BUDoPT domain prompt learner instead of CoOp or CoCoOp (ablation) | BUDoPT with CelebA-Spoof · Leave-one-out P1 (avg) | HTER: 2.61 / 2.53 -> 0.91 | Improved |
| add CelebA-Spoof as supplementary training data | BUDoPT · Leave-one-out P1 (avg) | HTER: 2.62 -> 0.91 | Improved |
| train on fewer source domains (MI instead of OCI/ICM) | BUDoPT · MI->O | HTER: 5.94 vs 2.26 | Mixed |
Closest papers by meaning
- DGPDL: Domain-Guided Prompt Distribution Learning for Generalizable Face Anti-Spoofing (TPAMI 2026 · similarity 0.92)
- CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing (CVPR 2024 · similarity 0.92)
- Test-Time Domain Generalization for Face Anti-Spoofing (CVPR 2024 · similarity 0.90)
- Gradient Alignment for Cross-Domain Face Anti-Spoofing (CVPR 2024 · similarity 0.89)
- FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models (AAAI 2026 · similarity 0.88)
- SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining (AAAI 2025 · similarity 0.88)
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.
