cs.CVNov 9, 2026

FMA-Net: Flexible Modality Adaptation for Robust Multimodal Face Presentation Attack Detection

Authors: Yuhao Gao, Yichen Shi, Zitong Yu, Hongyang Wang, Hongrui Li, Ruixin Zhang, Shouhong Ding, Jun Feng

Organizations: School of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang, China. · School of Integrated Circuit, Shanghai Jiao Tong University, Shanghai, China · Eastern Institute of Technology, Ningbo, Zhejiang, China. · School of Computing and Information Technology, Great Bay University, Dongguan, China. · 

Abstract

Multimodal face presentation attack detection (fPAD) improves robustness using complementary RGB, depth, and infrared (IR) cues, but deployment remains challenging when modalities are unavailable or incomplete. Existing flexible-modality methods mainly use zero-filling or modality omission, potentially discarding cross-modal information and introducing modality-dependent bias. We propose the Flexible Modality Adaptation Network (FMA-Net), a unified framework that compensates for missing modalities through instruction-guided latent-space translation. The Face Modality Instruct Translator (FMIT) estimates target modality observations from RGB inputs, while context-aware category enhancement uses learnable text prompts as modality-invariant semantic anchors. A Facial Feature Adapter (F2A) integrates global facial structure and local spoof-relevant cues to enhance discriminative representations. Synthetic-to-Real Face Domain Alignment (SR-FDA) reduces feature discrepancies between translated and real modalities, with benefits depending on the missing-modality pattern and data domain. Experiments on WMCA and PADISI-Face validate the framework. On WMCA with a 70% modality missing ratio, FMA-Net achieves a mean ACER of 3.22% across four intra-domain missing-modality protocols, compared with 4.24% for the strongest baseline by the same criterion. When both depth and IR are entirely unavailable, it achieves 5.23% ACER, compared with 5.99% for the best competing result. Cross-domain experiments also reveal limitations of synthetic-to-real alignment under dataset shifts. These results support FMA-Net as a practical approach to fPAD with flexible and incomplete modalities.

Figures & tables

Explore similar work

CardsList
  1. Foundation and Multimodal Large Language Models for Face Presentation and Morph Attack Detection

    Aug 30, 2026Hatef Otroshi Shahreza, Asif Hussain Khan, Peter Lorenz +2Image Forgery DetectionVision Foundation Model Adaptation

  2. LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection

    Aug 10, 2026Peter Lorenz, Anjith George, Marcel SébastienVision Foundation ModelsVision Foundation Model Adaptation

  3. Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark

    Jul 29, 2026Peter Lorenz, Anjith George, Sébastien MarcelVision Foundation ModelsLinear Probing