Research map / Label-efficient and robust learning / Domain adaptation and generalization
Instance-Aware Domain Generalization for Face Anti-Spoofing
Read the paperCheck 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 |
|---|---|---|---|
| add DKG to the baseline (ablation) | IADG · I&C&M to O | HTER (%): 19.75 -> 16.94 | Helped |
| add CSA after DKG (ablation) | IADG · I&C&M to O | HTER (%): 16.94 -> 12.50 | Helped |
| add AIAW after DKG and CSA (ablation) | IADG · I&C&M to O | HTER (%): 12.50 -> 8.86 | Helped |
| use AIAW instead of IW, GIW, or ISW (ablation) | IADG · I&C&M to O | HTER (%): 14.89, 14.13, 11.97 -> 8.86 | Helped |
| use asymmetric whitening rather than symmetric whitening (ablation) | IADG · I&C&M to O | HTER (%): 10.69 -> 8.86 | Helped |
| set the whitening ratio k_r:k_s to 1:0.2 (ablation) | IADG · I&C&M to O | HTER (%): 10.20 -> 8.86 | Helped |
| set the whitening ratio k_r:k_s to 1:0.1 instead of 1:0.2 (ablation) | IADG · I&C&M to O | HTER (%): 8.86 -> 9.86 | Hurt |
| use CSA rather than MixStyle (ablation) | IADG · I&C&M to O | HTER (%): 15.00 -> 8.86 | Helped |
| use CSA rather than SSA (ablation) | IADG · I&C&M to O | HTER (%): 13.29 -> 8.86 | Helped |
| use CSA rather than SHM (ablation) | IADG · I&C&M to O | HTER (%): 11.18 -> 8.86 | Helped |
| combine static and dynamic convolution branches rather than use static only (ablation) | IADG · I&C&M to O | HTER (%): 13.33 -> 8.6 | Helped |
| combine static and dynamic convolution branches rather than use dynamic only (ablation) | IADG · I&C&M to O | HTER (%): 12.18 -> 8.6 | Helped |
Closest papers by meaning
- Gradient Alignment for Cross-Domain Face Anti-Spoofing (CVPR 2024 · similarity 0.93)
- Test-Time Domain Generalization for Face Anti-Spoofing (CVPR 2024 · similarity 0.93)
- CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing (CVPR 2024 · similarity 0.91)
- 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 0.89)
- 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.