Abstract
In response to the increasing amount of deepfake content on the internet, a large number of deepfake detection methods have been recently developed. To our best knowledge, existing methods simply perform binary classification, i.e., they simply consider the deepfake images generated from different forgery methods as a single category. Unfortunately, different deepfake forgery methods usually generate deepfake images with different artifacts/appearances. Under such circumstance, a simple binary classification mechanism may limit the learning ability of the detection models, i.e., they may ignore certain forgery traces. Therefore, we propose a novel deepfake detection method via fine-grained classification and global-local information fusion. Specifically, we improve the binary classification task with a fine-grained classification mechanism, such that the deepfake detection model can learn more precise features for fake images from different forgery methods. Besides, we construct a global-local information fusion architecture to emphasize the important information in certain local regions and fuse them with global semantic information. In addition, we design a global center loss, which makes the real images features more cohesive and enlarge the distance between real and fake images features, to further enhance the generalization ability of the detection model. Extensive experiments demonstrate the effectiveness and superiority of our method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Afchar, D., Nozick, V., Yamagishi, J., Echizen, I.: Mesonet: a compact facial video forgery detection network. In: IEEE WIFS, pp. 1–7 (2018)
AI, G.: Contributing data to deepfake detection research (2019). https://ai.googleblog.com/2019/09/contributing-data-to-deepfake-detection.html. Accessed 09 Apr 2022
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: IEEE CVPR, pp. 1251–1258 (2017)
Dong, X., et al.: Protecting celebrities from deepfake with identity consistency transformer. In: IEEE/CVF CVPR, pp. 9468–9478 (2022)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Gunawan, T.S., Hanafiah, S.A.M., Kartiwi, M., Ismail, N., Za’bah, N.F., Nordin, A.N.: Development of photo forensics algorithm by detecting photoshop manipulation using error level analysis. Indones. J. Electr. Eng. Comput. Sci. 7(1), 131–137 (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
Li, J., Xie, H., Li, J., Wang, Z., Zhang, Y.: Frequency-aware discriminative feature learning supervised by single-center loss for face forgery detection. In: IEEE/CVF CVPR, pp. 6458–6467 (2021)
Li, L., et al.: Face x-ray for more general face forgery detection. In: IEEE/CVF CVPR, pp. 5001–5010 (2020)
Li, Y., Lyu, S.: Exposing DeepFake videos by detecting face warping artifacts. arXiv preprint arXiv:1811.00656 (2018)
Li, Y., Yang, X., Sun, P., Qi, H., Lyu, S.: Celeb-DF: a large-scale challenging dataset for DeepFake forensics. In: IEEE/CVF CVPR, pp. 3207–3216 (2020)
Liu, H., et al.: Spatial-phase shallow learning: rethinking face forgery detection in frequency domain. In: IEEE/CVF CVPR, pp. 772–781 (2021)
der Maaten, L.V., Hinton, G.: Visualizing data using t-SNE. JMLR 9(86), 2579–2605 (2008)
Masi, I., Killekar, A., Mascarenhas, R.M., Gurudatt, S.P., AbdAlmageed, W.: Two-branch recurrent network for isolating deepfakes in videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 667–684. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58571-6_39
Qian, Y., Yin, G., Sheng, L., Chen, Z., Shao, J.: Thinking in frequency: face forgery detection by mining frequency-aware clues. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 86–103. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58610-2_6
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nießner, M.: Faceforensics++: learning to detect manipulated facial images. In: IEEE/CVF ICCV, pp. 1–11 (2019)
Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: ICML, pp. 6105–6114. PMLR (2019)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Yang, X., Li, Y., Lyu, S.: Exposing deep fakes using inconsistent head poses. In: IEEE ICASSP, pp. 8261–8265 (2019)
Zhang, B., Li, S., Feng, G., Qian, Z., Zhang, X.: Patch diffusion: a general module for face manipulation detection. AAAI 36(3), 3243–3251 (2022)
Zhao, H., Zhou, W., Chen, D., Wei, T., Zhang, W., Yu, N.: Multi-attentional deepfake detection. In: IEEE/CVF CVPR, pp. 2185–2194 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, T., Guo, Y., Wang, Y. (2024). Deepfake Detection via Fine-Grained Classification and Global-Local Information Fusion. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14430. Springer, Singapore. https://doi.org/10.1007/978-981-99-8537-1_25
Download citation
DOI: https://doi.org/10.1007/978-981-99-8537-1_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8536-4
Online ISBN: 978-981-99-8537-1
eBook Packages: Computer ScienceComputer Science (R0)