Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 97 of the 113 references it cites were found in a registry or an index.

F 2 Trans: High-Frequency Fine-Grained Transformer for Face Forgery Detection

Miao, Changtao, Tan, Zichang, Chu, Qi, Liu, Huan, Hu, Honggang, Yu, Nenghai · 2023 · IEEE Transactions on Information Forensics and Security

Abstract

In recent years, face forgery detectors have aroused great interest and achieved impressive performance, but they are still struggling with generalization and robustness. In this work, we explore taking full advantage of the fine-grained forgery traces in both spatial and frequency domains to alleviate this issue. Specifically, we propose a novel High-Frequency Fine-Grained Transformer (F2Trans) network which contains two important components, namely Central Difference Attention (CDA) and High-frequency Wavelet Sampler (HWS). The premier CDA module is capable of capturing invariant fine-grained manipulation patterns by aggregating both pixel-level intensity and gradient information of the query to generate key and value pairs. Subsequently, the proposed HWS discards the low-frequency components of wavelet transformation and hierarchically explores high-frequency forgery cues of feature maps, which prevents model confusion caused by low-frequency components and pays attention to local frequency information. In addition, HWS can be employed as a special pooling layer for the F2Trans architecture to produce hierarchical feature representations in the spatial-frequency domain. Extensive experiments on multiple popular benchmarks demonstrate the generalization and robustness of the specially designed F2Trans framework is well-tailored for face forgery detection when confronting the cross-dataset, cross-manipulation, and unseen perturbations.

Overview

Integrity signals

Registry

Crossref · 10.1109/tifs.2022.3233774

Cites

97 of 97 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 113 references

Research works printed but not linked: 3

  1. 2019, DeepFakes
  2. 2019, FaceSwap
  3. Zhao, 2018, Deep learning for human-centric image analysis

Cited by

See all 172

Metadata

Authors
Miao, C., Tan, Z., Chu, Q., Liu, H., Hu, H., & Yu, N.
Affiliations
  • University of Science and Technology of China (CN)
  • Baidu (China) (CN)
  • Beijing Jiaotong University (CN)
Venue
IEEE Transactions on Information Forensics and Security
Published
2023
Volume
18
Pages
1039-1051
ISSN
  • 1556-6013 (ISSN-L)
  • 1556-6021
OpenAlex
W4313476637
Cited by
172
References
113
Citations by year
2026: 45 · 2025: 70 · 2024: 44 · 2023: 13
FWCI
15.55
Type
journal article
Language
en
Open access
closed
Locations
IEEE Transactions on Information Forensics and Security (publishedVersion)
Funders
  • National Natural Science Foundation of China (62002336, U20B2047)
  • Fund Project of University of Science and Technology of China (YD3480002001)
  • Fundamental Research Funds for the Central Universities
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
Keywords
face forgery detection, high-frequency characteristics, wavelet transform, transformer models, spatial frequency domain, generalization, robustness, cross-dataset generalization

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: F 2 Trans: High-Frequency Fine-Grained Transformer for Face Forgery Detection. https://app.cochat.ai/papers/10.1109/tifs.2022.3233774
The paper
Miao, C., Tan, Z., Chu, Q., Liu, H., Hu, H., & Yu, N. (2023). F 2 Trans: High-Frequency Fine-Grained Transformer for Face Forgery Detection. IEEE Transactions on Information Forensics and Security. https://doi.org/10.1109/tifs.2022.3233774

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.