Research map / Label-efficient and robust learning / Recognition and long-tail
Face Anti-Spoofing: Model Matters, so Does Data
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 |
|---|---|---|---|
| Add attended local spatial regions to the temporal path (ablation) | STASN · Oulu-NPU Protocol 1 | ACER(%): 2.5 -> 1.9 | Helped |
| Add attended local spatial regions to the temporal path (ablation) | STASN · Oulu-NPU Protocol 3 | ACER(%): 3.6±1.9 -> 2.8±1.6 | Helped |
| Use Grad-Gram to search for initial attended-region positions (ablation) | STASN · Oulu-NPU Protocol 1 | ACER(%): 2.3 -> 1.9 | Helped |
| Use Grad-Gram to search for initial attended-region positions (ablation) | STASN · Oulu-NPU Protocol 3 | ACER(%): 3.3±1.9 -> 2.8±1.6 | Helped |
| Pretrain the CNN with collected face anti-spoofing data | STASN · Oulu-NPU Protocol 1 | ACER(%): 1.9 -> 1.0 | Helped |
| Pretrain the CNN with collected face anti-spoofing data | STASN · Oulu-NPU Protocol 2 | ACER(%): 2.2 -> 1.1 | Helped |
| Pretrain the CNN with collected face anti-spoofing data | STASN · Oulu-NPU Protocol 3 | ACER(%): 2.8±1.6 -> 2.5±2.2 | Helped |
| Pretrain the CNN with collected face anti-spoofing data | STASN · Oulu-NPU Protocol 4 | ACER(%): 7.5±4.7 -> 2.6±2.8 | Helped |
| Pretrain the CNN with collected face anti-spoofing data | STASN · SiW Protocol 3 | ACER(%): 12.10±1.50 -> 5.85±0.85 | Helped |
| Pretrain the CNN with collected face anti-spoofing data | STASN · CASIA-MFSD train, Replay-Attack test | HTER: 31.5% -> 18.7% | Helped |
| Pretrain the CNN with collected face anti-spoofing data | STASN · Replay-Attack train, CASIA-MFSD test | HTER: 30.9% -> 25.0% | Helped |
Closest papers by meaning
- One-Class Face Anti-spoofing via Spoof Cue Map-Guided Feature Learning (CVPR 2024 · similarity 0.89)
- FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models (AAAI 2026 · similarity 0.88)
- Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing (CVPR 2025 · similarity 0.87)
- SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining (AAAI 2025 · similarity 0.87)
- Test-Time Domain Generalization for Face Anti-Spoofing (CVPR 2024 · similarity 0.86)
- From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing (CVPR 2026 · similarity 0.86)
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.