CoChat

MTD-Net: Learning to Detect Deepfakes Images by Multi-Scale Texture Difference

Yang, Jiachen, Li, Aiyun, Xiao, Shuai, Lu, Wen, Gao, Xinbo · 2021 · IEEE Transactions on Information Forensics and Security

The DOI matches its Crossref record; 60 of the 61 references it cites were found in a registry or an index.

Abstract

With the rapid development of face manipulation technology, it is difficult for human eyes to distinguish fake face images. On the contrary, Convolutional Neural Network (CNN) discriminators can quickly reach high accuracy in identifying fake/real face images. In this study, we explore the behavior of CNN models in distinguish fake/real faces. We find multi-scale texture difference information plays an important role in face forgery detection. Motivated by the above observation, we propose a new Multi-scale Texture Difference model coined as MTD-Net for robust face forgery detection, which leverages central difference convolution (CDC) and atrous spatial pyramid pooling (ASPP). CDC combines the pixel intensity information and the pixel gradient information to give a stationary description of texture difference information. Simultaneously, based on the ASPP, multi-scale information fusion can keep the texture features from being destroyed. Experimental results on several databases, Faceforensics++, DeeperForensics-1.0, Celeb-DF and DFDC prove that our MTD-Net outperforms existing approaches. The MTD-Net is more robust to image distortion, e.g., JPEG compression and blur, which is urgently needed in the wild world.

Overview

Integrity signals

Registry

Crossref · 10.1109/tifs.2021.3102487

Cites

60 of 60 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.

Citations

Cites

Show all 60 references

Research works printed but not linked: 3

  1. 2019, Deepfake
  2. 2019, Deepfake
  3. tolosana, 2020, DeepFakes evolution: Analysis of facial regions and fake detection performance, arXiv 2004 07532

Cited by

See all 184

Metadata

Authors
Yang, J., Li, A., Xiao, S., Lu, W., & Gao, X.
Affiliations
  • Tianjin University (CN)
  • Xidian University (CN)
  • Chongqing University of Posts and Telecommunications (CN)
Venue
IEEE Transactions on Information Forensics and Security
Published
2021
Volume
16
Pages
4234-4245
ISSN
  • 1556-6013 (ISSN-L)
  • 1556-6021
OpenAlex
W3191630110
Cited by
184
References
61
Citations by year
2026: 22 · 2025: 37 · 2024: 44 · 2023: 41 · 2022: 38 · 2021: 2
FWCI
11.24
Type
journal article
Language
en
Open access
closed
Locations
IEEE Transactions on Information Forensics and Security (publishedVersion)
Funders
  • National Natural Science Foundation of China (61871283)
  • Foundation of Pre-Research on Equipment of China (61400010304)
  • Major Civil-Military Integration Project in Tianjin, China (18ZXJMTG00170)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
Keywords
deepfake detection, face forgery detection, atrous spatial pyramid pooling, image distortion robustness, JPEG compression robustness, blur robustness

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: MTD-Net: Learning to Detect Deepfakes Images by Multi-Scale Texture Difference. https://app.cochat.ai/papers/10.1109/tifs.2021.3102487
The paper
Yang, J., Li, A., Xiao, S., Lu, W., & Gao, X. (2021). MTD-Net: Learning to Detect Deepfakes Images by Multi-Scale Texture Difference. IEEE Transactions on Information Forensics and Security. https://doi.org/10.1109/tifs.2021.3102487

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.