Research map / Label-efficient and robust learning / Domain adaptation and generalization
Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing
Seungjin Jung, Kanghee Lee, Yonghyun Jeong, Haeun Noh, Jungmin Lee, Jongwon Choi
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 GS-RM and FOD together to the base model (ablation) | GD-FAS · OCI->M | HTER: 2.92 -> 0.42 | Improved |
| add GS-RM alone (ablation) | GD-FAS base · OCI->M | HTER: 2.92 -> 2.50 | Improved |
| add FOD alone (ablation) | GD-FAS base · OCI->M | HTER: 2.92 -> 2.08 | Improved |
| add FOD alone to reduce calibration error (ablation) | GD-FAS base · OCI->M | ECE: 5.60 -> 1.60 | Improved |
| add GS-RM on top of FOD (ablation) | GD-FAS (FOD only) · OCI->M | ECE: 1.60 -> 3.39 | Hurt |
| add GS-RM on top of FOD (ablation) | GD-FAS (FOD only) · OCI->M | HTER: 2.08 -> 0.42 | Improved |
| add GS-RM alone (ablation) | GD-FAS base · OMI->C | HTER: 2.22 -> 2.22 | No clear effect |
| predict with image-text embedding similarity instead of classifier output (ablation) | GD-FAS · OCI->M | HTER: 2.50 -> 0.42 | Improved |
| replace text embeddings with random vectors (ablation) | GD-FAS · OCM->I | HTER: 3.33 -> 11.83 | Hurt |
| use batch size 16 instead of 3 (ablation) | GD-FAS · OCI->M | HTER: 5.00 -> 0.42 | Improved |
| increase batch size from 16 to 32 (ablation) | GD-FAS · ICM->O | HTER: 2.64 -> 3.01 | No clear effect |
| add extra CelebA-Spoof source data | GD-FAS · Average over 4 protocols | HTER: 1.83 -> 0.95 | Improved |
Closest papers by meaning
- Rethinking Domain Generalization for Face Anti-Spoofing: Separability and Alignment (CVPR 2023 · similarity 0.92)
- Gradient Alignment for Cross-Domain Face Anti-Spoofing (CVPR 2024 · similarity 0.92)
- Towards Unsupervised Domain Generalization for Face Anti-Spoofing (ICCV 2023 · similarity 0.92)
- Instance-Aware Domain Generalization for Face Anti-Spoofing (CVPR 2023 · similarity 0.92)
- Test-Time Domain Generalization for Face Anti-Spoofing (CVPR 2024 · similarity 0.89)
- Rethinking Generalizable Face Anti-spoofing via Hierarchical Prototype-guided Distribution Refinement in Hyperbolic Space (CVPR 2024 · similarity 0.89)
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.
