mlsanityData to 7 Oct 2026

Dual-Cross Central Difference Network for Face Anti-Spoofing

arXiv 2105.01290 ↗First posted 4 May 2021cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

Face anti-spoofing (FAS) plays a vital role in securing face recognition systems. Recently, central difference convolution (CDC) has shown its excellent representation capacity for the FAS task via leveraging local gradient features. However, aggregating central difference clues from all neighbors/directions simultaneously makes the CDC redundant and sub-optimized in the training phase. In this paper, we propose two Cross Central Difference Convolutions (C-CDC), which exploit the difference of the center and surround sparse local features from the horizontal/vertical and diagonal directions, respectively. It is interesting to find that, with only five ninth parameters and less computational cost, C-CDC even outperforms the full directional CDC. Based on these two decoupled C-CDC, a powerful Dual-Cross Central Difference Network (DC-CDN) is established with Cross Feature Interaction Modules (CFIM) for mutual relation mining and local detailed representation enhancement. Furthermore, a novel Patch Exchange (PE) augmentation strategy for FAS is proposed via simply exchanging the face patches as well as their dense labels from random samples. Thus, the augmented samples contain richer live/spoof patterns and diverse domain distributions, which benefits the intrinsic and robust feature learning. Comprehensive experiments are performed on four benchmark datasets with three testing protocols to demonstrate our state-of-the-art performance.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 4 May 2021.

Builds on

22 of 33 references.

References · 22

  1. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  2. 2017Deformable Convolutional Networkscited by 1,481
  3. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  4. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  5. 2020Exploring Self-attention for Image Recognitioncited by 313
  6. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  7. 2019Local Relation Networks for Image Recognitioncited by 210
  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. 2020NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofingcited by 104
  11. 2015face anti-spoofing based on color texture analysiscited by 82
  12. 2019Deep Pixel-wise Binary Supervision for Face Presentation Attack Detectioncited by 76
10 more
  1. 2019Deep Tree Learning for Zero-shot Face Anti-Spoofingcited by 73
  2. 2020Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofingcited by 70
  3. 2020Face Anti-Spoofing Via Disentangled Representation Learningcited by 65
  4. 2020Face Anti-Spoofing with Human Material Perceptioncited by 62
  5. 2020On Disentangling Spoof Trace for Generic Face Anti-Spoofingcited by 62
  6. 2018Face De-Spoofing: Anti-Spoofing via Noise Modelingcited by 60
  7. 2020Revisiting Pixel-Wise Supervision for Face Anti-Spoofingcited by 45
  8. 2019Learning Meta Model for Zero- and Few-shot Face Anti-spoofingcited by 44
  9. 2016Local Binary Convolutional Neural Networkscited by 38
  10. 2020Multi-Modal Face Anti-Spoofing Based on Central Difference Networkscited by 36

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 9; 2023: 15; 2024: 7; 2025: 4; 2026: 1.

47 papers.

Sort:

By area:

  1. 2021Pixel Difference Networks for Efficient Edge Detectioncited by 167
  2. 2023DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attentioncited by 90
  3. 2022Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofingcited by 73
  4. 2022PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognitioncited by 67
  5. 2021Deep Learning for Face Anti-Spoofing: A Surveycited by 64
  6. 2021Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofingcited by 49
  7. 2022Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofingcited by 38
  8. 2023Semantic Diffusion Network for Semantic Segmentationcited by 30
  9. 2021Learning Meta Pattern for Face Anti-Spoofingcited by 29
  10. 2022Adaptive Mixture of Experts Learning for Generalizable Face Anti-Spoofingcited by 28
  11. 2022Benchmarking Joint Face Spoofing and Forgery Detection with Visual and Physiological Cuescited by 24
  12. 2021Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learningcited by 20
35 more
  1. 2022Flexible-Modal Face Anti-Spoofing: A Benchmarkcited by 20
  2. 2024Test-Time Domain Generalization for Face Anti-Spoofingcited by 20
  3. 2023Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofingcited by 19
  4. 2021Structure Destruction and Content Combination for Face Anti-Spoofingcited by 18
  5. 20213D High-Fidelity Mask Face Presentation Attack Detection Challengecited by 18
  6. 2024Lightweight Pixel Difference Networks for Efficient Visual Representation Learningcited by 17
  7. 2024Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesiscited by 16
  8. 2022ViTransPAD: Video Transformer using convolution and self-attention for Face Presentation Attack Detectioncited by 14
  9. 2023Learnable Differencing Center for Nighttime Depth Perceptioncited by 14
  10. 2023S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokenscited by 11
  11. 2021Consistency Regularization for Deep Face Anti-Spoofingcited by 10
  12. 2024A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsamplingcited by 7
  13. 2021A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognitioncited by 6
  14. 2025FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Modelscited by 6
  15. 2021Taming Self-Supervised Learning for Presentation Attack Detection: De-Folding and De-Mixingcited by 5
  16. 2025SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretrainingcited by 5
  17. 2021Review of Face Presentation Attack Detection Competitionscited by 3
  18. 2023Liveness score-based regression neural networks for face anti-spoofingcited by 3
  19. 2023AdvFAS: A robust face anti-spoofing framework against adversarial examplescited by 3
  20. 2023Wild Face Anti-Spoofing Challenge 2023: Benchmark and Resultscited by 2
  21. 2023TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofingcited by 2
  22. 2024Few-shot Object Localizationcited by 2
  23. 2024Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systemscited by 2
  24. 2026YUV20K: A Complexity-Driven Benchmark and Trajectory-Aware Alignment Model for Video Camouflaged Object Detectioncited by 2
  25. 2022A Survey of Face Recognitioncited by 1
  26. 2023From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learningcited by 1
  27. 2023A Closer Look at Geometric Temporal Dynamics for Face Anti-Spoofingcited by 1
  28. 2023Hyperbolic Face Anti-Spoofingcited by 1
  29. 2023IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Imagescited by 1
  30. 2023Flow-Attention-based Spatio-Temporal Aggregation Network for 3D Mask Detectioncited by 1
  31. 2025PhenoProfiler: Advancing Phenotypic Learning for Image-based Drug Discoverycited by 1
  32. 2025Enhancing Learnable Descriptive Convolutional Vision Transformer for Face Anti-Spoofingcited by 1
  33. 2022Face Presentation Attack Detectioncited by 0
  34. 2023AdvGen: Physical Adversarial Attack on Face Presentation Attack Detection Systemscited by 0
  35. 2024Multi-Scale Temporal Difference Transformer for Video-Text Retrievalcited by 0