CoChat

Inconsistency-Aware Wavelet Dual-Branch Network for Face Forgery Detection

Jia, Gengyun, Zheng, Meisong, Hu, Chuanrui, Ma, Xin, Xu, Yuting, Liu, Luoqi, Deng, Yafeng, He, Ran · 2021 · IEEE Transactions on Biometrics, Behavior, and Identity Science
Cited by 62

The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.

Abstract

Current face forgery techniques can generate high-fidelity fake faces with extremely low labor and time costs. As a result, face forgery detection becomes an important research topic to prevent technology abuse. In this paper, we present an inconsistency-aware wavelet dual-branch network for face forgery detection. This model is mainly based on two kinds of forgery clues called inter-image and intra-image inconsistencies. To fully utilize them, we firstly enhance the forgery features by using additional inputs based on stationary wavelet decomposition (SWD). Then, considering the different properties of the two inconsistencies, we design a dual-branch network that predicts image-level and pixel-level forgery labels respectively. The segmentation branch aims to recognize real and fake local regions, which is crucial for discovering intra-image inconsistency. The classification branch learns to discriminate the real and fake images globally, thus can extract inter-image inconsistency. Finally, bilinear pooling is employed to fuse the features from the two branches. We find that the bilinear pooling is a kind of spatial attentive pooling. It effectively utilizes the rich spatial features learned by the segmentation branch. Experimental results show that the proposed method surpasses the state-of-the-art face forgery detection methods.

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/tbiom.2021.3086109

Cites

24 of 24 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 24 references

Research works printed but not linked: 37

  1. 10.1006/jbin.2001.1010 · doi:10.1006/jbin.2001.1010
  2. 10.1109/CVPR42600.2020.00473 · DOI · Paper page
  3. 10.1109/CVPR.2017.195 · DOI · Paper page
  4. dzanic, 2020, Fourier spectrum discrepancies in deep network generated images, Proc Adv Neural Inf Process Syst, 33
  5. agarwal, 2019, Protecting world leaders against deep fakes, Proc IEEE Int Conf Comput Vis Workshops, 38
  6. 10.1109/TIFS.2009.2033749 · DOI · Paper page
  7. fu, 2012, Forgery authentication in extreme wide-angle lens using distortion CUE and fake saliency map, IEEE Trans Inf Forensics Security, 7, 1301, 10.1109/TIFS.2012.2195492 · DOI
  8. 2020, Faceswap
  9. 2020, Deepfake
  10. 10.1109/CVPR42600.2020.00791 · DOI · Paper page
  11. 10.1109/TPAMI.2017.2723400 · DOI · Paper page
  12. 10.1109/WIFS.2017.8267647 · DOI · Paper page
  13. 10.1145/3306346.3323035 · DOI · Paper page
  14. 10.1145/2929464.2929475 · DOI · Paper page
  15. kingma, 2014, Auto-encoding variational Bayes, Proc Int Conf Learn Represent, 1
  16. 10.1109/TIFS.2021.3050065 · DOI
  17. 10.1109/CVPRW.2018.00121 · DOI · Paper page
  18. fu, 2019, Dual variational generation for low shot heterogeneous face recognition, Proc Adv Neural Inf Process Syst, 2670
  19. 10.1109/TPAMI.2021.3052549 · DOI
  20. ma, 2020, Free-form image inpainting via contrastive attention network, Proc Int Conf Pattern Recognit, 1
  21. 10.1007/s11263-019-01154-8 · DOI
  22. 10.1007/s11263-019-01267-0 · DOI
  23. 10.1109/ICCV.2017.244 · DOI · Paper page
  24. 10.1007/s11263-013-0688-y · DOI · Paper page
  25. 10.1109/TIFS.2012.2202227 · DOI · Paper page
  26. fan, 2003, Identification of bitmap compression history: JPEG detection and quantizer estimation, IEEE Trans Image Process, 12, 230, 10.1109/TIP.2002.807361 · DOI · Paper page
  27. 10.1109/TIFS.2010.2074194 · DOI · Paper page
  28. 10.1109/CVPR.2018.00116 · DOI · Paper page
  29. 10.1109/TIFS.2008.2012215 · DOI · Paper page
  30. 10.1109/CVPR42600.2020.00181 · DOI · Paper page
  31. goodfellow, 2014, Generative adversarial nets, Proc Adv Neural Inf Process Syst, 2672
  32. 10.1109/TPAMI.2016.2644615 · DOI · Paper page
  33. liu, 2015, Parsenet Looking wider to see better
  34. 10.1109/ICCV.2019.00317 · DOI
  35. 10.1109/ICCV.2019.00913 · DOI · Paper page
  36. 10.1109/ITNG.2012.13 · DOI
  37. 10.1109/ICDSP.2011.6004974 · DOI

Cited by

See all 62

Metadata

Authors
Jia, G., Zheng, M., Hu, C., Ma, X., Xu, Y., Liu, L., Deng, Y., & He, R.
Venue
IEEE Transactions on Biometrics, Behavior, and Identity Science
Published
2021-07
Volume
3
Issue
3
Pages
308-319
ISSN
2637-6407 (ISSN-L)
OpenAlex
W3166873596
Cited by
62
References
24
FWCI
3.17
Type
journal article
Language
en
Open access
closed
Funders
Beijing Natural Science Foundation (JQ18017)

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: Inconsistency-Aware Wavelet Dual-Branch Network for Face Forgery Detection. https://app.cochat.ai/papers/10.1109/tbiom.2021.3086109
The paper
Jia, G., Zheng, M., Hu, C., Ma, X., Xu, Y., Liu, L., Deng, Y., & He, R. (2021). Inconsistency-Aware Wavelet Dual-Branch Network for Face Forgery Detection. IEEE Transactions on Biometrics, Behavior, and Identity Science. https://doi.org/10.1109/tbiom.2021.3086109

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.