CoChat

Learning Second Order Local Anomaly for General Face Forgery Detection

Open access
Fei, Jianwei, Dai, Yunshu, Yu, Peipeng, Shen, Tianrun, Xia, Zhihua, Weng, Jian · 2022 · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 83

The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.

Abstract

In this work, we propose a novel method to improve the generalization ability of CNN-based face forgery detectors. Our method considers the feature anomalies of forged faces caused by the prevalent blending operations in face forgery algorithms. Specifically, we propose a weakly supervised Second Order Local Anomaly (SOLA) learning module to mine anomalies in local regions using deep feature maps. SOLA first decomposes the neighborhood of local features by different directions and distances and then calculates the first and second order local anomaly maps which provide more general forgery traces for the classifier. We also propose a Local Enhancement Module (LEM) to improve the discrimination between local features of real and forged regions, so as to ensure accuracy in calculating anomalies. Besides, an improved Adaptive Spatial Rich Model (ASRM) is introduced to help mine subtle noise features via learnable high pass filters. With neither pixel level annotations nor external synthetic data, our method using a simple ResNet18 backbone achieves competitive performances compared with state-of-the-art works when evaluated on unseen forgeries.

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/cvpr52688.2022.01963

Cites

34 of 34 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

Research works printed but not linked: 20

  1. 10.1109/CVPRW50498.2020.00338 · DOI · Paper page
  2. 10.1109/TIFS.2018.2825953 · DOI · Paper page
  3. 10.1109/ICME46284.2020.9102914 · DOI
  4. 10.1109/WIFS.2016.7823921 · DOI · Paper page
  5. 10.1109/CVPR42600.2020.00791 · DOI · Paper page
  6. 10.1016/j.patcog.2020.107696 · DOI
  7. 10.24963/ijcai.2021/102 · DOI · Paper page
  8. 10.1109/TBIOM.2021.3086109 · DOI · Paper page
  9. 10.1145/3394171.3414034 · DOI · Paper page
  10. Li, 2019, Exposing deep fake videos by de-tecting face warping artifacts
  11. Dufour, Deepfakedetection dataset
  12. Paszke, 2019, Pytorch: An imperative style, high-performance deep learning library, Ad-vances in neural information processingsystems, 32, 8026
  13. 10.1109/WIFS.2016.7823911 · DOI · Paper page
  14. 10.1109/ICCV48922.2021.01476 · DOI
  15. 10.1109/IJCB52358.2021.9484408 · DOI
  16. 10.1109/CVPRW53098.2021.00104 · DOI
  17. 10.1145/3306346.3323035 · DOI · Paper page
  18. Cozzolino, 2019, Extracting camera-based fingerprints for video forensics
  19. 10.1109/CVPR.2019.00977 · DOI · Paper page
  20. Peng, 2018, Learning rich features for image manipulation detection, 1053

Cited by

See all 83

Metadata

Authors
Fei, J., Dai, Y., Yu, P., Shen, T., Xia, Z., & Weng, J.
Venue
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2022-06
Pages
20238-20248
ISSN
1063-6919 (ISSN-L)
OpenAlex
W4313177092
Cited by
83
References
34
FWCI
6.95
Type
conference paper
Language
en
Open access
green
Funders
  • National Key Research and Development Plan of China (2020YFB1005600)
  • National Natural Science Foundation of China (62122032,U1936118)
  • Qinglan Project of Jiangsu Province, and “333” project of Jiangsu Province

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

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.