Flow Augmentation and Knowledge Distillation for Lightweight Face Presentation Attack Detection
Researchers have developed a new method for lightweight face presentation attack detection (FacePAD) that enhances motion cues during training without requiring explicit optical flow estimation at inference. A dual-branch teacher model fuses appearance and motion data, which is then distilled into an RGB-only student model. This approach allows the student to learn motion-sensitive representations efficiently, achieving high accuracy on several benchmarks while significantly reducing computational requirements for real-time deployment on resource-constrained devices. AI
IMPACT Introduces a more efficient approach to face anti-spoofing, enabling real-time deployment on edge devices.