BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-Spoofing

• URL: http://arxiv.org/abs/2412.18065v1
• Date: Tue, 24 Dec 2024 00:28:28 GMT
• Title: BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-Spoofing
• Abstract summary: multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks.<n>Existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts.<n>Our research introduces a Mixture of Experts (MoE) model to address these issues effectively.
• Score: 45.59998158610864
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts' inability to capture nuanced spoofing indicators; (2) Gated networks' susceptibility to input noise affecting decision-making; (3) MoE's sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://github.com/murInJ/BIG-MoE.

Related papers

• Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities [52.189426539304065]
  This paper introduces a paradigm shift that redefines multimodal forensics from conventional "feature fusion" to "modality generalization"<n>We propose the first modality-agnostic forgery (MAF) detection framework. By explicitly decoupling modality-specific styles, MAF precisely extracts the essential, cross-modal latent forgery knowledge.
  arXiv  Detail & Related papers  (2026-04-09T03:35:21Z)
• Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder [59.89996751196727]
  Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models.<n>SAEs' hidden layers have high dimensionality to satisfy sparsity constraints, resulting in prohibitive training and inference costs.<n>Recent Mixture of Experts (MoE) approaches attempt to address this by SAEs into narrower expert networks with gated activation.<n>We propose two key innovations: (1) Multiple Expert Activation that simultaneously engages semantically weighted expert subsets to encourage specialization, and (2) Feature Scaling that enhances diversity through adaptive high-frequency scaling.
  arXiv  Detail & Related papers  (2025-11-07T22:19:34Z)
• Filling the Gaps: A Multitask Hybrid Multiscale Generative Framework for Missing Modality in Remote Sensing Semantic Segmentation [28.992992584085787]
  Multimodal learning has shown significant performance boost compared to ordinary unimodal models.<n>In real-world scenarios, multimodal signals are susceptible to missing because of sensor failures and adverse weather conditions.<n>We propose a novel Generative-Enhanced MultiModal learning Network (GEMMNet) to tackle these limitations.
  arXiv  Detail & Related papers  (2025-09-14T05:40:35Z)
• Multi-Modal Face Anti-Spoofing via Cross-Modal Feature Transitions [2.3505792985856813]
  Multi-modal face anti-spoofing (FAS) aims to detect genuine human presence by extracting liveness cues from multiple modalities.<n>We propose a novel Cross-modal Transition-guided Network (CTNet) to tackle the challenges in the multi-modal FAS task.
  arXiv  Detail & Related papers  (2025-07-08T01:24:14Z)
• Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization [52.87635234206178]
  This paper proposes a new framework, namely MoNFAP, specifically tailored for multi-face manipulation detection and localization. The framework incorporates two novel modules: the Forgery-aware Unified Predictor (FUP) Module and the Mixture-of-Noises Module (MNM)
  arXiv  Detail & Related papers  (2024-08-05T08:35:59Z)
• MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection [54.545054873239295]
  Deepfakes have recently raised significant trust issues and security concerns among the public. ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance. This work introduces Mixture-of-Experts modules for Face Forgery Detection (MoE-FFD), a generalized yet parameter-efficient ViT-based approach.
  arXiv  Detail & Related papers  (2024-04-12T13:02:08Z)
• Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing [26.901402236963374]
  Face Anti-Spoofing (FAS) is crucial for securing face recognition systems against presentation attacks. Many multi-modal FAS approaches have emerged, but they face challenges in generalizing to unseen attacks and deployment conditions.
  arXiv  Detail & Related papers  (2024-02-29T16:06:36Z)
• Generative-based Fusion Mechanism for Multi-Modal Tracking [35.77340348091937]
  We introduce Conditional Generative Adversarial Networks (CGANs) and Diffusion Models (DMs) We condition these multi-modal features with random noise in the GM framework, effectively transforming the original training samples into harder instances. This design excels at extracting discriminative clues from the features, enhancing the ultimate tracking performance.
  arXiv  Detail & Related papers  (2023-09-04T17:22:10Z)
• Cross-Attention is Not Enough: Incongruity-Aware Dynamic Hierarchical Fusion for Multimodal Affect Recognition [69.32305810128994]
  Incongruity between modalities poses a challenge for multimodal fusion, especially in affect recognition. We propose the Hierarchical Crossmodal Transformer with Dynamic Modality Gating (HCT-DMG), a lightweight incongruity-aware model. HCT-DMG: 1) outperforms previous multimodal models with a reduced size of approximately 0.8M parameters; 2) recognizes hard samples where incongruity makes affect recognition difficult; 3) mitigates the incongruity at the latent level in crossmodal attention.
  arXiv  Detail & Related papers  (2023-05-23T01:24:15Z)
• M3FAS: An Accurate and Robust MultiModal Mobile Face Anti-Spoofing System [39.37647248710612]
  Face presentation attacks (FPA) have brought increasing concerns to the public through various malicious applications. We devise an accurate and robust MultiModal Mobile Face Anti-Spoofing system named M3FAS.
  arXiv  Detail & Related papers  (2023-01-30T12:37:04Z)
• Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning [54.15303628138665]
  Face anti-spoofing (FAS) plays a vital role in preventing face recognition systems from presentation attacks. Existing face anti-spoofing datasets lack diversity due to the insufficient identity and insignificant variance. We propose Dual Spoof Disentanglement Generation framework to tackle this challenge by "anti-spoofing via generation"
  arXiv  Detail & Related papers  (2021-12-01T15:36:59Z)
• Face Anti-Spoofing with Human Material Perception [76.4844593082362]
  Face anti-spoofing (FAS) plays a vital role in securing the face recognition systems from presentation attacks. We rephrase face anti-spoofing as a material recognition problem and combine it with classical human material perception. We propose the Bilateral Convolutional Networks (BCN), which is able to capture intrinsic material-based patterns.
  arXiv  Detail & Related papers  (2020-07-04T18:25:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.