.png){kind=icon}
.png){kind=icon}
Return
Flexible Modal Mixture-of-Experts With Inter-Modal Knowledge Distillation for Face Anti-Spoofing
.png){kind=icon}
PRE
AI
H
A
N
Y
H
张
J
Z
J
Z
Z
梁
DOI：10.1109/tifs.2026.3714100.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Flexible Modal Face Anti-Spoofing (FAS) aims to improve the model’s adaptability to any given deployment modality. The current methods commonly use multiple independent encoders to learn modality-general features for flexible testing, which inevitably involves redundant computation. In this work, we propose a novel Flexible Modal Mixture-of-Experts (FM-MoE) for adaptively learning the representation of multi-modal data in a unified framework, which includes Modal Inter-MoE and Modal Intra-MoE. Specifically, considering that the challenge of flexible modal tasks lies in significant modal differences that make it difficult for classifiers to identify subtle spoofing clues, we employed Modal Inter-MoE to learn modality-general and modality-specific features, respectively. Meanwhile, to more effectively capture multi-modal visual information, the Modal Intra-MoE replaces the traditional routing patch token strategy, focusing on extracting instance-level spoofing clues from the channel perspective in the feature map. In addition, to avoid the imbalance problem caused by simultaneous training of multi-modal data, we introduce Modal Inter Knowledge Distillation Loss (MI-KDL), which includes Cross-Modal Loss and Shared to Multi-Modal Loss (CML & S2MML). CML is designed to enhance information alignment across different modalities, while S2MML endeavors to transfer shared knowledge to all modalities, preventing the model from excessively optimizing certain single modalities. We conduct extensive experiments to demonstrate the flexibility and superiority of our FM-MoE framework over the state-of-the-art methods.
Keywords:
Flexible modal face anti-spoofing
flexible modal mixture-of-experts
modal inter-MoE
modal intra-MoE
modal inter knowledge distillation loss
cross-modal loss
shared to multi-modal loss
Journal
IF:
8
Papers:
5.2K
Citations:
2.3W
Organization
Cited Papers