mlsanityData to 7 Oct 2026

Generalizing Face Forgery Detection with High-frequency Features

arXiv 2103.12376 ↗First posted 23 Mar 2021cs.CVcited by 261

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Current face forgery detection methods achieve high accuracy under the within-database scenario where training and testing forgeries are synthesized by the same algorithm. However, few of them gain satisfying performance under the cross-database scenario where training and testing forgeries are synthesized by different algorithms. In this paper, we find that current CNN-based detectors tend to overfit to method-specific color textures and thus fail to generalize. Observing that image noises remove color textures and expose discrepancies between authentic and tampered regions, we propose to utilize the high-frequency noises for face forgery detection. We carefully devise three functional modules to take full advantage of the high-frequency features. The first is the multi-scale high-frequency feature extraction module that extracts high-frequency noises at multiple scales and composes a novel modality. The second is the residual-guided spatial attention module that guides the low-level RGB feature extractor to concentrate more on forgery traces from a new perspective. The last is the cross-modality attention module that leverages the correlation between the two complementary modalities to promote feature learning for each other. Comprehensive evaluations on several benchmark databases corroborate the superior generalization performance of our proposed method.

Key facts. Cited by 261 papers in the map (data through 7 Oct 2026). Builds on 34 of its 57 references that are in the map. First posted on arXiv 23 Mar 2021.

Builds on

34 of 57 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  7. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  8. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  9. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  10. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  11. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  12. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
22 more
  1. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 518
  2. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  3. 2018MesoNet: a Compact Facial Video Forgery Detection Networkcited by 409
  4. 2018Exposing DeepFake Videos By Detecting Face Warping Artifactscited by 318
  5. 2018Additive Margin Softmax for Face Verificationcited by 275
  6. 2019Cross-Modal Self-Attention Network for Referring Image Segmentationcited by 263
  7. 2019On the Detection of Digital Face Manipulationcited by 259
  8. 2020DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detectioncited by 251
  9. 2020Global Texture Enhancement for Fake Face Detection in the Wildcited by 220
  10. 2019Cross Attention Network for Few-shot Classificationcited by 218
  11. 2018Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videoscited by 180
  12. 2018Learning Rich Features for Image Manipulation Detectioncited by 154
  13. 2019Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videoscited by 130
  14. 2018Two-Stream Neural Networks for Tampered Face Detectioncited by 125
  15. 2018ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detectioncited by 104
  16. 2019Unmasking DeepFakes with simple Featurescited by 78
  17. 2019Occlusion Robust Face Recognition Based on Mask Learning with PairwiseDifferential Siamese Networkcited by 51
  18. 2016Areas of Attention for Image Captioningcited by 23
  19. 2019Towards Generalizable Deepfake Detection with Locality-aware AutoEncodercited by 17
  20. 2020AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detectioncited by 16
  21. 2020One-Shot Domain Adaptation For Face Generationcited by 15
  22. 2019Complement Face Forensic Detection and Localization with FacialLandmarkscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 36; 2023: 51; 2024: 58; 2025: 70; 2026: 39.

261 papers.

Sort:

By area:

  1. 2022Detecting Deepfakes with Self-Blended Imagescited by 332
  2. 2023UCF: Uncovering Common Features for Generalizable Deepfake Detectioncited by 177
  3. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  4. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 162
  5. 2024PuLID: Pure and Lightning ID Customization via Contrastive Alignmentcited by 143
  6. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  7. 2024DF40: Toward Next-Generation Deepfake Detectioncited by 126
  8. 2024C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detectioncited by 111
  9. 2024Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detectioncited by 102
  10. 2021Dual Contrastive Learning for General Face Forgery Detectioncited by 100
  11. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
  12. 2022CORE: Consistent Representation Learning for Face Forgery Detectioncited by 73
38 more
  1. 2024Preserving Fairness Generalization in Deepfake Detectioncited by 70
  2. 2023Inserting Anybody in Diffusion Models via Celeb Basiscited by 63
  3. 2021Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learningcited by 60
  4. 2024Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuningcited by 57
  5. 2023Detecting and Grounding Multi-Modal Media Manipulation and Beyondcited by 55
  6. 2023Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detectioncited by 50
  7. 2022Deepfake Detection: A Comprehensive Survey from the Reliability Perspectivecited by 48
  8. 2024FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledgecited by 48
  9. 2024Can We Leave Deepfake Data Behind in Training Deepfake Detector?cited by 48
  10. 2024Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detectioncited by 47
  11. 2022Exploring Frequency Adversarial Attacks for Face Forgery Detectioncited by 45
  12. 2023Towards General Visual-Linguistic Face Forgery Detectioncited by 45
  13. 2022Audio-Visual Person-of-Interest DeepFake Detectioncited by 43
  14. 2022Delving into Sequential Patches for Deepfake Detectioncited by 41
  15. 2024FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMscited by 38
  16. 2022Exploring Disentangled Content Information for Face Forgery Detectioncited by 36
  17. 2022Learning Second Order Local Anomaly for General Face Forgery Detectioncited by 36
  18. 2023Robustness and Generalizability of Deepfake Detection: A Study with Diffusion Modelscited by 36
  19. 2024X2-DFD: A framework for eXplainable and eXtendable Deepfake Detectioncited by 35
  20. 2022Detecting and Recovering Sequential DeepFake Manipulationcited by 34
  21. 2022Explaining Deepfake Detection by Analysing Image Matchingcited by 34
  22. 2024Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detectioncited by 30
  23. 2023Parents and Children: Distinguishing Multimodal DeepFakes from Natural Imagescited by 29
  24. 2024DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusioncited by 29
  25. 2024AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmarkcited by 28
  26. 2024MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detectioncited by 27
  27. 2025Exploring Unbiased Deepfake Detection via Token-Level Shuffling and Mixingcited by 27
  28. 2023DeepFake-Adapter: Dual-Level Adapter for DeepFake Detectioncited by 26
  29. 2023Locate and Verify: A Two-Stream Network for Improved Deepfake Detectioncited by 26
  30. 2022Discovering Transferable Forensic Features for CNN-generated Images Detectioncited by 24
  31. 2022MINTIME: Multi-Identity Size-Invariant Video Deepfake Detectioncited by 23
  32. 2023Continual Face Forgery Detection via Historical Distribution Preservingcited by 23
  33. 2023QKSAN: A Quantum Kernel Self-Attention Networkcited by 23
  34. 2023DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Cluescited by 23
  35. 2025ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localizationcited by 22
  36. 2023Controllable Guide-Space for Generalizable Face Forgery Detectioncited by 21
  37. 2024LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarkscited by 21
  38. 2024Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learningcited by 20

50 most cited of 261 All 261 (JSON)