Learning Features of Intra-Consistency and Inter-Diversity: Keys Toward Generalizable Deepfake Detection
The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
Public concerns about deepfake face forgery are continually rising in recent years. Most deepfake detection approaches attempt to learn discriminative features between real and fake faces through end-to-end trained deep neural networks. However, the majorities of them suffer from the problem of poor generalization across different data sources, forgery methods, and/or post-processing operations. In this paper, following the simple but effective principle in discriminative representation learning, i.e., towards learning features of intra-consistency within classes and inter-diversity between classes, we leverage a novel transformer-based self-supervised learning method and an effective data augmentation strategy towards generalizable deepfake detection. Considering the differences between the real and fake images are often subtle and local, the proposed method firstly utilizes Self Prediction Learning (SPL) to learn rich hidden representations by predicting masked patches at a pre-training stage. Intra-class consistency clues in images can be mined without deepfake labels. After pre-training, the discrimination model is then fine-tuned via multi-task learning, including a deepfake classification task and a forgery mask estimation task. It is facilitated by our new data augmentation method called Adjustable Forgery Synthesizer (AFS), which can conveniently simulate the process of synthesizing deepfake images with various levels of visual reality in an explicit manner. AFS greatly prevents overfitting due to insufficient diversity in training data. Comprehensive experiments demonstrate that our method outperforms the state-of-the-art competitors on several popular benchmark datasets in terms of generalization to unseen forgery methods and untrained datasets.
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.
Integrity signals
Registry
Cites
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.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Self-citationEnd-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489
FaceForensics++: Learning to Detect Manipulated Facial Images
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Niessner, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00009 · Cited by 3,314 · cited 3×
“FaceForensics++ (FF++) [44] contains 1,000 original videos and 5,000 fake videos forged by five manipulation methods, i.”
BackgroundMethodCeleb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00327 · Cited by 1,846 · cited 1×
“Celeb-DF [48] applies a more advanced deepfake technique to celebrity videos downloaded from YouTube and also has two kinds of video compression quality: high-quality (c23) and low-quality (c40).”
MethodFace2Face: Real-Time Face Capture and Reenactment of RGB Videos
Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., & Niessner, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.262 · Cited by 1,747
Face X-Ray for More General Face Forgery Detection
Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., & Guo, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00505 · Cited by 1,211
Exposing Deep Fakes Using Inconsistent Head Poses
Yang, X., Li, Y., & Lyu, S. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8683164 · Cited by 1,196
In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking
Li, Y., Chang, M.-C., & Lyu, S. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630787 · Cited by 1,089
Research works printed but not linked: 21
- 10.1109/TCSVT.2021.3106047 · DOI
- 10.1109/TCSVT.2021.3089724 · DOI
- 10.1109/TCSVT.2021.3133859 · DOI · Paper page
- Chen, A simple framework for contrastive learning of visual representations, 1597
- Zhou, 2022, Self pre-training with masked autoencoders for medical image analysis, arXiv:2203.05573 · arXiv
- Vaswani, Attention is all you need, 30, 5998
- Dosovitskiy, An image is worth 16×16 words: Transformers for image recognition at scale, 1
- 10.1145/3474085.3475535 · DOI · Paper page
- 10.1109/TIFS.2022.3146781 · DOI · Paper page
- 10.1609/aaai.v36i1.19954 · DOI · Paper page
- 10.1109/TCSVT.2021.3074259 · DOI · Paper page
- 10.1109/CVPR52688.2022.00925 · DOI · Paper page
- 10.1109/CVPR42600.2020.00975 · DOI · Paper page
- 10.1109/CVPR52688.2022.00943 · DOI · Paper page
- Bao, BEiT: BERT pre-training of image transformers
- 10.1109/TBIOM.2021.3086109 · DOI · Paper page
- 10.1145/3306346.3323035 · DOI · Paper page
- 2022, Contributing Data to Deepfake Detection Research
- Tan, EfficientNet: Rethinking model scaling for convolutional neural networks, 6105
- 10.1109/ICCV.2017.74 · DOI · Paper page
- Van der Maaten, 2008, Visualizing data using t-SNE, J. Mach. Learn. Res., 9, 1
Cited by
PVASS-MDD: Predictive Visual-Audio Alignment Self-Supervision for Multimodal Deepfake Detection
Yu, Y., Liu, X., Ni, R., Yang, S., Zhao, Y., & Kot, A. C. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3309899 · Cited by 63
Exploring autonomous methods for deepfake detection: A detailed survey on techniques and evaluation
Sunil, R., Mer, P., Diwan, A., Mahadeva, R., & Sharma, A. (2025) · Heliyon · doi:10.1016/j.heliyon.2025.e42273 · Cited by 54
She, H., Hu, Y., Liu, B., Li, J., & Li, C.-T. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3451356 · Cited by 24
“Following the evaluation protocol in [63], [64], and [65], we conduct cross-dataset between different subsets in the FF ++ (C23).”
MethodAutonomous detection and evaluation of deepfakes: a comprehensive study
Sunil, R., Mer, P., & Diwan, A. (2023) · 2023 Seventh International Conference on Image Information Processing (ICIIP) · doi:10.1109/iciip61524.2023.10537789 · Cited by 4
Metadata
- Authors
- Chen, H., Lin, Y., Li, B., & Tan, S.
- Venue
- IEEE Transactions on Circuits and Systems for Video Technology
- Published
- 2023-03
- Volume
- 33
- Issue
- 3
- Pages
- 1468-1480
- ISSN
- 1051-8215 (ISSN-L)
- 1558-2205
- OpenAlex
- W4297095254
- Cited by
- 80
- References
- 34
- FWCI
- 5.99
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Funders
- NSFC (61872244, 62272314)
- Basic and Applied Basic Research Foundation of Guangdong Province (2019B151502001)
- Shenzhen Research and Development Program (JCYJ20200109105008228)
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: Learning Features of Intra-Consistency and Inter-Diversity: Keys Toward Generalizable Deepfake Detection. https://app.cochat.ai/papers/10.1109/tcsvt.2022.3209336
- The paper
- Chen, H., Lin, Y., Li, B., & Tan, S. (2023). Learning Features of Intra-Consistency and Inter-Diversity: Keys Toward Generalizable Deepfake Detection. IEEE Transactions on Circuits and Systems for Video Technology. https://doi.org/10.1109/tcsvt.2022.3209336
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.