FeatureTransfer: Unsupervised Domain Adaptation for Cross-Domain Deepfake Detection
Open accessThe DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Abstract
Recently, various Deepfake detection methods have been proposed, and most of them are based on convolutional neural networks (CNNs). These detection methods suffer from overfitting on the source dataset and do not perform well on cross-domain datasets which have different distributions from the source dataset. To address these limitations, a new method named FeatureTransfer is proposed in this paper, which is a two-stage Deepfake detection method combining with transfer learning. Firstly, The CNN model pretrained on a third-party large-scale Deepfake dataset can be used to extract the more transferable feature vectors of Deepfake videos in the source and target domains. Secondly, these feature vectors are fed into the domain-adversarial neural network based on backpropagation (BP-DANN) for unsupervised domain adaptive training, where the videos in the source domain have real or fake labels, while the videos in the target domain are unlabelled. The experimental results indicate that the proposed method FeatureTransfer can effectively solve the overfitting problem in Deepfake detection and greatly improve the performance of cross-dataset evaluation.
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.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The feature vectors derived from CNN are utilized in Backpropagation Based on Domain-Adversarial Neural Network (BP-DANN) for adversarial TL, leading to higher efficiency than end-to-end adversarial learning.”
From Deepfake detection using deep learning methods: A systematic and comprehensive review (2024) · cites this paper as Chen and Tan (2021)
Experimental — accuracy not yet measured
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
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667 · cited 2×
“(e proposed method is compared with previous Deepfake detection methods, including Xception [16], FSSpotter [18], Face X-Ray [22], and se_resnext101_32× 4 d [37].”
BackgroundMethodLearning Transferable Features with Deep Adaptation Networks
Long, M., Cao, Y., Wang, J., & Jordan, M. I. (2015) · arXiv · doi:10.48550/arxiv.1502.02791 · Cited by 4,505 · cited 1×
“For instance, correlation alignment (CORAL) [28] and maximum mean discrepancy (MMD) [29] are used to reduce the distribution divergence between domains.”
MethodDeep CORAL: Correlation Alignment for Deep Domain Adaptation
Sun, B., & Saenko, K. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-49409-8_35 · Cited by 3,757 · cited 1×
“For instance, correlation alignment (CORAL) [28] and maximum mean discrepancy (MMD) [29] are used to reduce the distribution divergence between domains.”
MethodFaceForensics++: 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 12×
“(e FaceForensics++ (FF) [16] dataset contains 1000 pristine (P) videos and 4000 fake videos generated by using the four most advanced facial manipulation methods, including DeepFakes (DF), Face2Face (F2F), FaceSwap (FS), and NeuralTextures (NT).”
BackgroundMethodInfluentialDlib-ml: A Machine Learning Toolkit
King, D. E. (2009) · doi:10.5555/1577069.1755843 · Cited by 2,777 · cited 1×
“As for face detection [7–9], MTCNN (multitask convolutional neural network) [7] and dlib [8] are mostly used as face detectors.”
MethodUnsupervised Domain Adaptation by Backpropagation
Ganin, Y., & Lempitsky, V. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.7495 · Cited by 2,521 · cited 1×
“Some works are based on discrepancy measurement domain-adversarial learning, such as domain-adversarial neural network (DANN) [30], multiadversarial domain adaptation (MADA) [31], and 2 Security and Communication Networks”
BackgroundSqueeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G. Z., & Wu, E. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.01507 · Cited by 1,908 · cited 2×
“(e proposed method is compared with previous Deepfake detection methods, including Xception [16], FSSpotter [18], Face X-Ray [22], and se_resnext101_32× 4 d [37].”
BackgroundMethodMesoNet: a Compact Facial Video Forgery Detection Network
Afchar, D., Nozick, V., Yamagishi, J., & Echizen, I. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630761 · Cited by 1,872 · cited 2×
“Based on this, they proposed that CNN can be used to learn the checkerboard effect characteristics to detect Deepfake videos by directly inputting the face images extracted from video frames, such as MesoNet [15] and XceptionNet [16].”
MethodCeleb-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 7×
“[19] found that most of the Deepfake detection methods trained and tested on specific datasets can achieve satisfactory performance, but their performances are significantly reduced when themethods are tested on cross-domain datasets, indicating that these methods are overfitting on a specific dataset.”
BackgroundMethodInfluentialDeepfake Video Detection Using Recurrent Neural Networks
Guera, D., & Delp, E. J. (2018) · 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2018.8639163 · Cited by 1,285 · cited 1×
“To detect the Deepfake images or videos, most of the previous works are based on deep learning methods, which can be categorized into two detectionmethods: CNN-basedmethods [10, 13, 15, 16, 20–22] and RCNN-based methods [11, 17, 18].”
Method
Cited by
Deepfake detection using deep learning methods: A systematic and comprehensive review
Heidari, A., Jafari Navimipour, N., Dag, H., & Unal, M. (2024) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1520 · Cited by 349
“Likewise, Chen and Tan (2021) introduced feature transfer, a two-stage deepfake detection approach that relies on unsupervised domain adaption.”
BackgroundA Novel Blockchain-Based Deepfake Detection Method Using Federated and Deep Learning Models
Heidari, A., Navimipour, N. J., Dag, H., Talebi, S., & Unal, M. (2024) · Cognitive Computation · doi:10.1007/s12559-024-10255-7 · Cited by 164
“Chen and Tan [42] introduced feature transfer, a two-stage deepfake detection approach that relies on unsupervised domain adaption.”
Fruits Classification and Detection Application Using Deep Learning
Mimma, N.-E.-A., Ahmed, S., Rahman, T., & Khan, R. (2022) · Scientific Programming · doi:10.1155/2022/4194874 · Cited by 70
“According to this approach, the deep learning model was initially trained on source images and evaluated on a dataset from a diferent source [27].”
MethodDeepFake on Face and Expression Swap: A Review
Waseem, S., Abu Bakar, S. A. R. S., Ahmed, B. A., Omar, Z., Eisa, T. A. E., & Dalam, M. E. E. (2023) · IEEE Access · doi:10.1109/access.2023.3324403 · Cited by 65
“Chen et al. [164] proposed a novel two-stage deepfake detection method called FeatureTransfer that leverages transfer learning.”
MethodDeepfakes: evolution and trends
Gil, R., Virgili‐Gomà, J., López, J. M., & García, R. (2023) · Soft Computing · doi:10.1007/s00500-023-08605-y · Cited by 50
“…Li et al. (2021b), Lu et al. (2021), Su et al. (2021), Luo et al. (2021), Biswas et al. (2021), Jiang et al. (2021), Korshunov and Marcel (2021), Chen and Tan (2021), Jin et al. (2021), Khalil et al. (2021), Gu et al. (2021), Yang et al. (2021c), Chintha et al. (2020a), Younus and Hasan…”
Metadata
- Authors
- Chen, B., & Tan, S.
- Affiliations
- Shenzhen University (CN)
- Corresponding author
- Tan, Shunquan
- Venue
- Security and Communication Networks
- Publisher
- Wiley
- Published
- 2021-06-07
- Volume
- 2021
- Pages
- 1-8
- ISSN
- 1939-0114 (ISSN-L)
- 1939-0122
- OpenAlex
- W3172431060
- Cited by
- 23
- References
- 41
- Citations by year
- 2026: 2 · 2025: 6 · 2024: 8 · 2023: 5 · 2022: 2
- FWCI
- 1.35
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Security and Communication Networks (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- Key-Area Research and Development Program of Guangdong Province (2019B010139003, 61772349, U19B2022, 61872244, 2019B151502001, JCYJ20180305124325555)
- National Natural Science Foundation of China (2019B010139003, 61772349, U19B2022, 61872244, 2019B151502001, JCYJ20180305124325555)
- Guangdong Basic and Applied Basic Research Foundation (2019B010139003, 61772349, U19B2022, 61872244, 2019B151502001, JCYJ20180305124325555)
- Shenzhen R&D Program (2019B010139003, 61772349, U19B2022, 61872244, 2019B151502001, JCYJ20180305124325555)
- Alibaba Group through Alibaba Innovative Research (AIR) Program (2019B010139003, 61772349, U19B2022, 61872244, 2019B151502001, JCYJ20180305124325555)
- 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
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- deepfake detection, unsupervised domain adaptation, domain generalization, transfer learning, domain adversarial neural networks, overfitting, feature extraction
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: FeatureTransfer: Unsupervised Domain Adaptation for Cross-Domain Deepfake Detection. https://app.cochat.ai/papers/10.1155/2021/9942754
- The paper
- Chen, B., & Tan, S. (2021). FeatureTransfer: Unsupervised Domain Adaptation for Cross-Domain Deepfake Detection. Security and Communication Networks. https://doi.org/10.1155/2021/9942754
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.