# Robust Multi-Modal Face Anti-Spoofing with Domain Adaptation: Tackling Missing Modalities, Noisy Pseudo-Labels, and Model Degradation

arXiv: https://arxiv.org/abs/2509.23475 · HTML: https://mlsanity.com/paper/2509.23475/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 45 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision](https://mlsanity.com/paper/1803.11097/) (2018)
- [Single-Side Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2004.14043/) (2020)
- [Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Network](https://mlsanity.com/paper/1909.08848/) (2019)
- [Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing](https://mlsanity.com/paper/2203.05340/) (2022)
- [CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing](https://mlsanity.com/paper/2003.05136/) (2020)
- [Test-Time Adaptation via Self-Training with Nearest Neighbor Information](https://mlsanity.com/paper/2207.10792/) (2022)
- [Face Anti-Spoofing with Human Material Perception](https://mlsanity.com/paper/2007.02157/) (2020)
- [CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing](https://mlsanity.com/paper/1908.10654/) (2019)
- [Towards Real-Time Monocular Depth Estimation for Robotics: A Survey](https://mlsanity.com/paper/2111.08600/) (2021)
- [Self-Domain Adaptation for Face Anti-Spoofing](https://mlsanity.com/paper/2102.12129/) (2021)
- [Instance-Aware Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2304.05640/) (2023)
- [Cross Modal Focal Loss for RGBD Face Anti-Spoofing](https://mlsanity.com/paper/2103.00948/) (2021)
- [Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing](https://mlsanity.com/paper/2203.12175/) (2022)
- [Multi-Modal Face Anti-Spoofing Based on Central Difference Networks](https://mlsanity.com/paper/2004.08388/) (2020)
- [Detection and Continual Learning of Novel Face Presentation Attacks](https://mlsanity.com/paper/2108.12081/) (2021)
- [Generative Domain Adaptation for Face Anti-Spoofing](https://mlsanity.com/paper/2207.10015/) (2022)
- [FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofing](https://mlsanity.com/paper/2305.03277/) (2023)
- [Flexible-Modal Face Anti-Spoofing: A Benchmark](https://mlsanity.com/paper/2202.08192/) (2022)
- [Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing](https://mlsanity.com/paper/2302.05744/) (2023)
- [Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing](https://mlsanity.com/paper/2402.19298/) (2024)
- [Cyclically Disentangled Feature Translation for Face Anti-spoofing](https://mlsanity.com/paper/2212.03651/) (2022)
- [Visual Prompt Flexible-Modal Face Anti-Spoofing](https://mlsanity.com/paper/2307.13958/) (2023)
- [PipeNet: Selective Modal Pipeline of Fusion Network for Multi-Modal Face Anti-Spoofing](https://mlsanity.com/paper/2004.11744/) (2020)
- [SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining](https://mlsanity.com/paper/2503.19982/) (2025)
- [Progressive Modality Cooperation for Multi-Modality Domain Adaptation](https://mlsanity.com/paper/2506.19316/) (2025)

## Abstract (arXiv)

Recent multi-modal face anti-spoofing (FAS) methods have investigated the potential of leveraging multiple modalities to distinguish live and spoof faces. However, pre-adapted multi-modal FAS models often fail to detect unseen attacks from new target domains. Although a more realistic domain adaptation (DA) scenario has been proposed for single-modal FAS to learn specific spoof attacks during inference, DA remains unexplored in multi-modal FAS methods. In this paper, we propose a novel framework, MFAS-DANet, to address three major challenges in multi-modal FAS under the DA scenario: missing modalities, noisy pseudo labels, and model degradation. First, to tackle the issue of missing modalities, we propose extracting complementary features from other modalities to substitute missing modality features or enhance existing ones. Next, to reduce the impact of noisy pseudo labels during model adaptation, we propose deriving reliable pseudo labels by leveraging prediction uncertainty across different modalities. Finally, to prevent model degradation, we design an adaptive mechanism that decreases the loss weight during unstable adaptations and increasing it during stable ones. Extensive experiments demonstrate the effectiveness and state-of-the-art performance of our proposed MFAS-DANet.