mlsanityData to 7 Oct 2026

CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing

arXiv 2403.14333 ↗First posted 21 Mar 2024cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

Domain generalization (DG) based Face Anti-Spoofing (FAS) aims to improve the model's performance on unseen domains. Existing methods either rely on domain labels to align domain-invariant feature spaces, or disentangle generalizable features from the whole sample, which inevitably lead to the distortion of semantic feature structures and achieve limited generalization. In this work, we make use of large-scale VLMs like CLIP and leverage the textual feature to dynamically adjust the classifier's weights for exploring generalizable visual features. Specifically, we propose a novel Class Free Prompt Learning (CFPL) paradigm for DG FAS, which utilizes two lightweight transformers, namely Content Q-Former (CQF) and Style Q-Former (SQF), to learn the different semantic prompts conditioned on content and style features by using a set of learnable query vectors, respectively. Thus, the generalizable prompt can be learned by two improvements: (1) A Prompt-Text Matched (PTM) supervision is introduced to ensure CQF learns visual representation that is most informative of the content description. (2) A Diversified Style Prompt (DSP) technology is proposed to diversify the learning of style prompts by mixing feature statistics between instance-specific styles. Finally, the learned text features modulate visual features to generalization through the designed Prompt Modulation (PM). Extensive experiments show that the CFPL is effective and outperforms the state-of-the-art methods on several cross-domain datasets.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 42 of its 61 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

42 of 61 references.

References · 42

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  3. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  5. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  6. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  7. 2021Domain Generalization with MixStylecited by 563
  8. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 316
  9. 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 180
  10. 2020Searching Central Difference Convolutional Networks for Face Anti-Spoofingcited by 173
  11. 2018Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervisioncited by 167
  12. 2020Single-Side Domain Generalization for Face Anti-Spoofingcited by 139
30 more
  1. 2020CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotationscited by 109
  2. 2020NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofingcited by 104
  3. 2019Regularized Fine-grained Meta Face Anti-spoofingcited by 86
  4. 2019Deep Pixel-wise Binary Supervision for Face Presentation Attack Detectioncited by 76
  5. 2019Deep Tree Learning for Zero-shot Face Anti-Spoofingcited by 73
  6. 2022Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofingcited by 73
  7. 2020Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofingcited by 70
  8. 2022PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognitioncited by 67
  9. 2020CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofingcited by 66
  10. 2020Face Anti-Spoofing Via Disentangled Representation Learningcited by 65
  11. 2019CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofingcited by 61
  12. 2021Self-Domain Adaptation for Face Anti-Spoofingcited by 49
  13. 2021Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofingcited by 49
  14. 2021Dual Reweighting Domain Generalization for Face Presentation Attack Detectioncited by 47
  15. 2023Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignmentcited by 47
  16. 2023FLIP: Cross-domain Face Anti-spoofing with Language Guidancecited by 45
  17. 2021Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detectioncited by 43
  18. 2023Instance-Aware Domain Generalization for Face Anti-Spoofingcited by 42
  19. 2021Cross Modal Focal Loss for RGBD Face Anti-Spoofingcited by 41
  20. 2022Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofingcited by 38
  21. 2021Meta-Teacher For Face Anti-Spoofingcited by 33
  22. 2022Adaptive Mixture of Experts Learning for Generalizable Face Anti-Spoofingcited by 28
  23. 2023FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofingcited by 22
  24. 2022Flexible-Modal Face Anti-Spoofing: A Benchmarkcited by 20
  25. 20213D High-Fidelity Mask Face Presentation Attack Detection Challengecited by 18
  26. 2023MA-ViT: Modality-Agnostic Vision Transformers for Face Anti-Spoofingcited by 18
  27. 2023Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulationcited by 14
  28. 2023Surveillance Face Anti-spoofingcited by 12
  29. 2023Compound Text-Guided Prompt Tuning via Image-Adaptive Cuescited by 7
  30. 2023Surveillance Face Presentation Attack Detection Challengecited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 19; 2026: 10.

39 papers.

Sort:

By area:

  1. 2024On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detectioncited by 40
  2. 2024FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learningcited by 21
  3. 2025LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognitioncited by 12
  4. 2024MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detectioncited by 11
  5. 2024Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Cluescited by 8
  6. 2024La-SoftMoE CLIP for Unified Physical-Digital Face Attack Detectioncited by 8
  7. 2025Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineeringcited by 7
  8. 2025Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transportcited by 6
  9. 2025FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Modelscited by 6
  10. 2025Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofingcited by 5
  11. 2025Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuningcited by 5
  12. 2025Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face Anti-Spoofingcited by 5
27 more
  1. 2026Benchmarking Vision Foundation Models for Domain-Generalizable Face Anti-Spoofingcited by 4
  2. 2024Unified Physical-Digital Attack Detection Challengecited by 3
  3. 2025FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detectioncited by 3
  4. 2025InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofingcited by 3
  5. 2024SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognitioncited by 2
  6. 2025SUEDE:Shared Unified Experts for Physical-Digital Face Attack Detection Enhancementcited by 2
  7. 2025Learning Knowledge-based Prompts for Robust 3D Mask Presentation Attack Detectioncited by 2
  8. 2025Self-supervised Feature Disentanglement and Augmentation Network for One-class Face Anti-spoofingcited by 1
  9. 2025Think Twice before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptationcited by 1
  10. 2025Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofingcited by 1
  11. 2025Multi-View Slot Attention Using Paraphrased Texts for Face Anti-Spoofingcited by 1
  12. 2026CPG-PAD: Concept-Informed Prompts Guided Presentation Attack Detectioncited by 1
  13. 2026Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmarkcited by 1
  14. 2024A Unified Framework for Iris Anti-Spoofing: Introducing Iris Anti-Spoofing Cross-Domain-Testing Protocol and Masked-MoE Methodcited by 0
  15. 2024Revisiting Face Forgery Detection: From Facial Representation to Forgery Detectioncited by 0
  16. 2024Spoof Trace Discovery for Deep Learning Based Explainable Face Anti-Spoofingcited by 0
  17. 2025Introducing Nylon Face Mask Attacks: A Dataset for Evaluating Generalised Face Presentation Attack Detectioncited by 0
  18. 2025Consolidating Diffusion-Generated Video Detection with Unified Multimodal Forgery Learningcited by 0
  19. 2025Open Set Face Forgery Detection via Dual-Level Evidence Collectioncited by 0
  20. 2025Spoofing-aware Prompt Learning for Unified Physical-Digital Facial Attack Detectioncited by 0
  21. 2026Domain-generalizable Face Anti-Spoofing with Patch-based Multi-tasking and Artifact Pattern Conversioncited by 0
  22. 2026UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoningcited by 0
  23. 2026MFVLR: Multi-domain Fine-grained Vision-Language Reconstruction for Generalizable Diffusion Face Forgery Detection and Localizationcited by 0
  24. 2026DINO-VPT: Hierarchical Visual Prompt Tuning for Joint Physical-Digital Face Anti-Spoofingcited by 0
  25. 2026LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detectioncited by 0
  26. 2026EXPL-FR: Explaining Face Recognition Models via Vision-Language Alignmentcited by 0
  27. 2026Foundation and Multimodal Large Language Models for Face Presentation and Morph Attack Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning Unknown Spoof Prompts for Generalized Face Anti-Spoofing Using Only Real Face Images
  2. 2023TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing
  3. 2026From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing
  4. 2025Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language Models
  5. 2025Exploring Task-Solving Paradigm for Generalized Cross-Domain Face Anti-Spoofing via Reinforcement Fine-Tuning
  6. 2026FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing
  7. 2025SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining
  8. 2024DiffFAS: Face Anti-Spoofing via Generative Diffusion Models