CoChat

Hierarchical Frequency-Assisted Interactive Networks for Face Manipulation Detection

Miao, Changtao, Tan, Zichang, Chu, Qi, Yu, Nenghai, Guo, Guodong · 2022 · IEEE Transactions on Information Forensics and Security
Cited by 110

The DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.

Abstract

Recently, face manipulation techniques have caused increasing trust concerns in our society. Although current face manipulation detection methods achieve impressive performance regarding intra-dataset evaluation, they are struggling to improve the generalization and robustness ability. To address this issue, we propose a novel Hierarchical Frequency-assisted Interactive Networks (HFI-Net) to explore comprehensive frequency-related forgery cues for face manipulation detection. At first, we formulate HFI-Net as a dual-branch network to take full advantage of both CNN and transformer for capturing local details and global context information, respectively. Considering the forged faces are easy to show flaws in the frequency domain, a novel Frequency-based Feature Refinement (FFR) module is proposed to learn frequency-based attention from RGB features. FFR module emphasizes forgery cues and suppresses the pristine semantics information by keeping middle-high frequency features while discarding the low-frequency ones. Based on FFR, we further develop a co-sharing Global-Local Interaction (GLI) module to conduct frequency-assisted interactions while capturing complementarity among dual branches. Lastly, we further implement the GLI module in each stage of the network to effectively explore multi-level frequency artifacts. Extensive experiments are conducted on several popular benchmarks including FaceForensics++, Celeb-DF, DeepFake-TIMIT, DFDC, UADFV, and DeeperForensics-1.0, which shows that our model outperforms the state-of-the-art, especially in unseen datasets, manipulations, and perturbations evaluation.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tifs.2022.3198275

Cites

44 of 44 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 44 references

Research works printed but not linked: 40

  1. 2019, DeepFakes
  2. 10.1145/3306346.3323035 · DOI · Paper page
  3. Dosovitskiy, 2020, An image is worth 16×16 words: Transformers for image recognition at scale, arXiv:2010.11929 · arXiv
  4. 2019, FaceSwap
  5. 10.1109/TIFS.2021.3050065 · DOI
  6. 10.1109/CVPR.2016.262 · DOI · Paper page
  7. 10.1145/3072959.3073640 · DOI · Paper page
  8. 10.24963/ijcai.2020/476 · DOI · Paper page
  9. 10.1145/3394171.3414034 · DOI · Paper page
  10. 10.1109/TIFS.2020.3045937 · DOI
  11. Zhou, 2021, Refiner: Refining self-attention for vision transformers, arXiv:2106.03714 · arXiv
  12. 10.1109/ICCV48922.2021.00042 · DOI · Paper page
  13. Touvron, Training data-efficient image transformers & distillation through attention, 10347
  14. Wodajo, 2021, Deepfake video detection using convolutional vision transformer, arXiv:2102.11126 · arXiv
  15. 10.1109/VCIP53242.2021.9675331 · DOI
  16. 10.1109/CVPR.2017.195 · DOI · Paper page
  17. 10.1109/TBIOM.2021.3119403 · DOI
  18. 10.1109/CVPR42600.2020.00181 · DOI · Paper page
  19. 10.1109/ICCV48922.2021.00082 · DOI · Paper page
  20. 10.1109/TIFS.2015.2506548 · DOI
  21. 10.1109/TIFS.2016.2623589 · DOI
  22. 10.1109/WACV48630.2021.00122 · DOI · Paper page
  23. 10.1109/TIFS.2021.3065495 · DOI
  24. 10.1109/ICME52920.2022.9859586 · DOI
  25. 10.1109/CVPR46437.2021.00361 · DOI · Paper page
  26. 10.1109/CVPRW53098.2021.00109 · DOI
  27. 10.1109/ICCV.2019.00765 · DOI · Paper page
  28. Yu, 2020, Responsible disclosure of generative models using scalable fingerprinting, arXiv:2012.08726 · arXiv
  29. Vaswani, Attention is all you need, 5998
  30. 10.1145/3474085.3475202 · DOI · Paper page
  31. Mao, Dual-stream network for visual recognition, 34, 25346
  32. 10.1109/CVPR.2018.00474 · DOI · Paper page
  33. Li, 2019, Celeb-DF: A large-scale challenging dataset for DeepFake forensics, arXiv:1909.12962 · arXiv
  34. 10.1609/aaai.v35i3.16367 · DOI · Paper page
  35. 10.1109/34.192463 · DOI · Paper page
  36. 10.1109/CVPR.2018.00745 · DOI · Paper page
  37. 10.1109/WIFS.2017.8267647 · DOI · Paper page
  38. Cozzolino, 2018, ForensicTransfer: Weakly-supervised domain adaptation for forgery detection, arXiv:1812.02510 · arXiv
  39. 10.1609/aaai.v32i1.11596 · DOI · Paper page
  40. 10.1007/978-3-319-46484-8_2 · DOI · Paper page

Cited by

See all 110

Metadata

Authors
Miao, C., Tan, Z., Chu, Q., Yu, N., & Guo, G.
Venue
IEEE Transactions on Information Forensics and Security
Published
2022
Volume
17
Pages
3008-3021
ISSN
  • 1556-6013 (ISSN-L)
  • 1556-6021
OpenAlex
W4290994941
Cited by
110
References
44
FWCI
7.04
Type
journal article
Language
en
Open access
closed
Funders
  • National Natural Science Foundation of China (62002336, U20B2047)
  • Fund Project of University of Science and Technology of China (YD3480002001)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Hierarchical Frequency-Assisted Interactive Networks for Face Manipulation Detection. https://app.cochat.ai/papers/10.1109/tifs.2022.3198275
The paper
Miao, C., Tan, Z., Chu, Q., Yu, N., & Guo, G. (2022). Hierarchical Frequency-Assisted Interactive Networks for Face Manipulation Detection. IEEE Transactions on Information Forensics and Security. https://doi.org/10.1109/tifs.2022.3198275

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.