TMFD: Two-Stage Meta-learning Feature Disentanglement Framework for DeepFake Detection
Abstract
With the advancement of deep neural networks (DNN), detecting falsified facial images has become a significant challenge. Previous state-of-the-art methods used fake images generated by various techniques as positive samples during the training phase. This strategy ensures that the model is exposed to a wide range of fake generation methods, resulting in a substantially higher number of positive samples than negative ones. However, in real-world scenarios, authentic images distinctly outnumber fake ones, which is not consistent with the hypothesis of designing DNN-based forensics detectors. Furthermore, the excessive use of certain fake images for training DNNs may lead to overfitting to specific fake generation techniques. Current research indicates that detectors often learn semantic features of the images, which can affect their performance. To address this issue, we propose a two-stage meta-learning feature disentanglement framework (TMFD). By leveraging the prior knowledge of meta-learning and incorporating a fine-tuning stage, extensive experimental results demonstrate that our method performs excellently across different domains.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Commonly used techniques for adaptive learning include meta-learning, incremental learning, knowledge distillation, and domain generalization.
“Common used techniques include meta-learning [20, 182-184], incremental learning [185], knowledge distillation [186], and domain generalization [187].”
From Deepfake detection across image, video, and audio: a comprehensive survey with empirical evaluation of generalization and robustness (2026) · cites this paper as [184]
Cites
Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain
Liu, H., Li, X., Zhou, W., Chen, Y., He, Y., Xue, H., Zhang, W., & Yu, N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00083 · Cited by 600 · see citing works
Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection
Haliassos, A., Vougioukas, K., Petridis, S., & Pantic, M. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00500 · Cited by 537 · see citing works
Detecting Deepfakes with Self-Blended Images
Shiohara, K., & Yamasaki, T. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01816 · Cited by 503 · see citing works
End-to-End Reconstruction-Classification Learning for Face Forgery Detection
Cao, J., Ma, C., Yao, T., Chen, S., Ding, S., & Yang, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00408 · Cited by 428 · see citing works
The deepfake detection challenge (dfdc) dataset
Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., & Ferrer, C. C. (2020) · arXiv · doi:10.48550/arxiv.2006.07397 · Cited by 427 · see citing works
Implicit identity leakage: The stumbling block to improving deepfake detection generalization
Dong, S., Wang, J., Ji, R., Liang, J., Fan, H., & Ge, Z. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00389 · Cited by 220 · see citing works
CORE: Consistent Representation Learning for Face Forgery Detection
Ni, Y., Meng, D., Yu, C., Quan, C., Ren, D., & Zhao, Y. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00011 · Cited by 136 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Nguyen-Le, H.-H., Tran, V.-T., Nguyen, D.-T., & Le-Khac, N.-A. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11608-4 · Cited by 1 · see citing works
- Authors
- Zhu, X., Lin, B., He, X., Xu, J., & Ding, F.
- Affiliations
- Nanchang University (CN)
- Venue
- 2024 IEEE International Joint Conference on Biometrics (IJCB)
- Publisher
- IEEE
- Published
- 2024-09-15
- Pages
- 1-8
- OpenAlex
- W4404238827
- Cited by
- 2
- References
- 7
- Citations by year
- 2026: 1 · 2025: 1
- FWCI
- 0.41
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Joint Conference on Biometrics (IJCB) (publishedVersion)
- Funders
- National Natural Science Foundation of China
- Key Research and Development Program of Jiangxi Province
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- deepfake detection, meta-learning, feature disentanglement, two-stage framework, fine-tuning, imbalanced training data, semantic features
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
