Shuai, Chao;
Zhong, Jieming;
Wu, Shuang;
Lin, Feng;
Wang, Zhibo;
Ba, Zhongjie;
Liu, Zhenguang;
... Ren, Kui; + view all
(2023)
Locate and Verify: A Two-Stream Network for Improved Deepfake Detection.
In:
Proceedings of the 31st ACM International Conference on Multimedia.
(pp. pp. 7131-7142).
ACM (Association for Computing Machinery)
Preview |
Text
2309.11131v1.pdf - Accepted Version Download (4MB) | Preview |
Abstract
Deepfake has taken the world by storm, triggering a trust crisis. Current deepfake detection methods are typically inadequate in generalizability, with a tendency to overfit to image contents such as the background, which are frequently occurring but relatively unimportant in the training dataset. Furthermore, current methods heavily rely on a few dominant forgery regions and may ignore other equally important regions, leading to inadequate uncovering of forgery cues. In this paper, we strive to address these shortcomings from three aspects: (1) We propose an innovative two-stream network that effectively enlarges the potential regions from which the model extracts forgery evidence. (2) We devise three functional modules to handle the multi-stream and multi-scale features in a collaborative learning scheme. (3) Confronted with the challenge of obtaining forgery annotations, we propose a Semi-supervised Patch Similarity Learning strategy to estimate patch-level forged location annotations. Empirically, our method demonstrates significantly improved robustness and generalizability, outperforming previous methods on six benchmarks, and improving the frame-level AUC on Deepfake Detection Challenge preview dataset from 0.797 to 0.835 and video-level AUC on CelebDF-v1 dataset from 0.811 to 0.847. Our implementation is available at https://github.com/sccsok/Locate-and-Verify.
| Type: | Proceedings paper |
|---|---|
| Title: | Locate and Verify: A Two-Stream Network for Improved Deepfake Detection |
| Event: | MM '23: The 31st ACM International Conference on Multimedia |
| Location: | Ottawa, Canada |
| Dates: | 29th October 2023 - 3rd November 2023 |
| ISBN-13: | 979-8-4007-0108-5 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3581783.3612386 |
| Publisher version: | http://dx.doi.org/10.1145/3581783.3612386 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10200415 |
Archive Staff Only
 |
View Item |
