Flow Augmentation and Knowledge Distillation for Lightweight Face Presentation Attack Detection

TL;DR

This paper introduces a method combining optical flow-based motion cues with knowledge distillation to create a lightweight, real-time face presentation attack detection model that maintains high accuracy without explicit flow computation during inference.

Contribution

The work proposes a dual-branch teacher model with flow-enhanced motion features and a knowledge distillation framework to train efficient RGB-only student models for FacePAD.

Findings

Achieved 0.0% HTER on Replay-Attack and Replay-Mobile datasets.

Student model runs at 52 FPS on NVIDIA Jetson Orin Nano.

Distilled student outperforms or matches teacher performance with fewer parameters.

Abstract

Face presentation attack detection (FacePAD) remains challenging under diverse spoofing representation, including 2D print and replay, 3D mask-based spoofing, makeup-induced appearance manipulation, and physical occlusions, as well as under varying capture conditions. Motion cues are highly discriminative for FacePAD but typically require explicit optical flow estimation, which introduces substantial computational overhead and limits real-time deployment. In this work, we leverage optical flow to enhance motion representation during training while eliminating the need for flow computation at inference. We propose a dual-branch teacher model that fuses appearance cues from RGB frames with motion cues derived from colorwheel-encoded optical flow, enabling effective modeling of micro-motions and temporal consistency. To enable efficient deployment, we introduce a knowledge distillation framework that transfers motion-aware knowledge from the flow-augmented teacher to a lightweight RGB-only student via logit distillation. As a result, the student implicitly learns motion-sensitive representations without requiring explicit flow estimation or additional feature extraction blocks at inference. Extensive experiments demonstrate strong performance across multiple benchmarks, achieving 0.0% HTER on Replay-Attack and Replay-Mobile, 0.94% HTER on ROSE-Youtu, 5.65% HTER on SiW-Mv2, and 0.42% ACER on OULU-NPU. The distilled student achieves performance comparable to or better than the teacher while significantly reducing parameters and FLOPs, achieving 52 FPS on an NVIDIA Jetson Orin Nano, indicating its suitability for real-time and resource-constrained FacePAD deployment.