mlsanityData to 7 Oct 2026

Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing

arXiv 2203.12175 ↗First posted 23 Mar 2022cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

While recent face anti-spoofing methods perform well under the intra-domain setups, an effective approach needs to account for much larger appearance variations of images acquired in complex scenes with different sensors for robust performance. In this paper, we present adaptive vision transformers (ViT) for robust cross-domain face antispoofing. Specifically, we adopt ViT as a backbone to exploit its strength to account for long-range dependencies among pixels. We further introduce the ensemble adapters module and feature-wise transformation layers in the ViT to adapt to different domains for robust performance with a few samples. Experiments on several benchmark datasets show that the proposed models achieve both robust and competitive performance against the state-of-the-art methods for cross-domain face anti-spoofing using a few samples.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 53 of its 82 references that are in the map. First posted on arXiv 23 Mar 2022.

Builds on

53 of 82 references.

References · 53

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  9. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
  10. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  11. 2020Transformer Interpretability Beyond Attention Visualizationcited by 620
  12. 2021Domain Generalization with MixStylecited by 563
38 more
  1. 2020Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stoppingcited by 377
  2. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
  3. 2017Data Augmentation Generative Adversarial Networkscited by 278
  4. 2018DropBlock: A regularization method for convolutional networkscited by 261
  5. 2018Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Taskscited by 214
  6. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  7. 2018Low-Shot Learning from Imaginary Datacited by 181
  8. 2020Searching Central Difference Convolutional Networks for Face Anti-Spoofingcited by 173
  9. 2018Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervisioncited by 167
  10. 2019Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Modelscited by 141
  11. 2020Single-Side Domain Generalization for Face Anti-Spoofingcited by 139
  12. 2017Few-Shot Adversarial Domain Adaptationcited by 111
  13. 2020CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotationscited by 109
  14. 2020NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofingcited by 104
  15. 2020Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learningcited by 93
  16. 2019Regularized Fine-grained Meta Face Anti-spoofingcited by 86
  17. 2015face anti-spoofing based on color texture analysiscited by 82
  18. 2014Learn Convolutional Neural Network for Face Anti-Spoofingcited by 80
  19. 2019Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Networkcited by 78
  20. 2019Deep Tree Learning for Zero-shot Face Anti-Spoofingcited by 73
  21. 2020CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofingcited by 66
  22. 2020Face Anti-Spoofing Via Disentangled Representation Learningcited by 65
  23. 2020Face Anti-Spoofing with Human Material Perceptioncited by 62
  24. 2020On Disentangling Spoof Trace for Generic Face Anti-Spoofingcited by 62
  25. 2019CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofingcited by 61
  26. 2018A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofingcited by 51
  27. 2021Self-Domain Adaptation for Face Anti-Spoofingcited by 49
  28. 2021Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofingcited by 49
  29. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  30. 2020Few-shot Domain Adaptation by Causal Mechanism Transfercited by 47
  31. 2021Dual-Cross Central Difference Network for Face Anti-Spoofingcited by 47
  32. 2021Dual Reweighting Domain Generalization for Face Presentation Attack Detectioncited by 47
  33. 2021Generalizable Representation Learning for Mixture Domain Face Anti-Spoofingcited by 46
  34. 2019Learning Meta Model for Zero- and Few-shot Face Anti-spoofingcited by 44
  35. 2020On the Effectiveness of Vision Transformers for Zero-shot Face Anti-Spoofingcited by 44
  36. 2019d-SNE: Domain Adaptation using Stochastic Neighborhood Embeddingcited by 40
  37. 2020Cross-ethnicity Face Anti-spoofing Recognition Challenge: A Reviewcited by 25
  38. 2021Feature Generation and Hypothesis Verification for Reliable Face Anti-Spoofingcited by 23

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 13; 2024: 12; 2025: 10; 2026: 3.

38 papers.

Sort:

By area:

  1. 2023Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignmentcited by 47
  2. 2023FLIP: Cross-domain Face Anti-spoofing with Language Guidancecited by 45
  3. 2024CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofingcited by 39
  4. 2024Gradient Alignment for Cross-Domain Face Anti-Spoofingcited by 26
  5. 2023FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofingcited by 22
  6. 2024FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learningcited by 21
  7. 2024Test-Time Domain Generalization for Face Anti-Spoofingcited by 20
  8. 2023Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofingcited by 19
  9. 2024Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesiscited by 16
  10. 2025FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detectioncited by 14
  11. 2025MADation: Face Morphing Attack Detection with Foundation Modelscited by 14
  12. 2023Surveillance Face Anti-spoofingcited by 12
26 more
  1. 2023Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Lesscited by 12
  2. 2023S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokenscited by 11
  3. 2024Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Cluescited by 8
  4. 2023Face Presentation Attack Detection by Excavating Causal Clues and Adapting Embedding Statisticscited by 7
  5. 2025Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineeringcited by 7
  6. 2023Domain Generalization via Ensemble Stacking for Face Presentation Attack Detectioncited by 6
  7. 2024Confidence Aware Learning for Reliable Face Anti-spoofingcited by 5
  8. 2025Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofingcited by 5
  9. 2025Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face Anti-Spoofingcited by 5
  10. 2025DADM: Dual Alignment of Domain and Modality for Face Anti-spoofingcited by 4
  11. 2024Unified Physical-Digital Attack Detection Challengecited by 3
  12. 2023Robust face anti-spoofing framework with Convolutional Vision Transformercited by 2
  13. 2025Learning Knowledge-based Prompts for Robust 3D Mask Presentation Attack Detectioncited by 2
  14. 2023EnfoMax: Domain Entropy and Mutual Information Maximization for Domain Generalized Face Anti-spoofingcited by 1
  15. 2023Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformercited by 1
  16. 2024Liveness Detection in Computer Vision: Transformer-based Self-Supervised Learning for Face Anti-Spoofingcited by 1
  17. 2024G2V2former: Graph Guided Video Vision Transformer for Face Anti-Spoofingcited by 1
  18. 2025Enhancing Learnable Descriptive Convolutional Vision Transformer for Face Anti-Spoofingcited by 1
  19. 2025Multi-View Slot Attention Using Paraphrased Texts for Face Anti-Spoofingcited by 1
  20. 2026CPG-PAD: Concept-Informed Prompts Guided Presentation Attack Detectioncited by 1
  21. 2026Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmarkcited by 1
  22. 2023FedSIS: Federated Split Learning with Intermediate Representation Sampling for Privacy-preserving Generalized Face Presentation Attack Detectioncited by 0
  23. 2024Advancing Cross-Domain Generalizability in Face Anti-Spoofing: Insights, Design, and Metricscited by 0
  24. 2024Spoof Trace Discovery for Deep Learning Based Explainable Face Anti-Spoofingcited by 0
  25. 2025Robust Multi-Modal Face Anti-Spoofing with Domain Adaptation: Tackling Missing Modalities, Noisy Pseudo-Labels, and Model Degradationcited by 0
  26. 2026LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detectioncited by 0