Pan, Kun;
Yin, Yifang;
Wei, Yao;
Lin, Feng;
Ba, Zhongjie;
Liu, Zhenguang;
Wang, Zhibo;
... Ren, Kui; + view all
(2023)
DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues.
In:
MM '23: Proceedings of the 31st ACM International Conference on Multimedia.
(pp. pp. 8035-8046).
ACM (Association for Computing Machinery)
Preview |
Text
2309.09526v1.pdf - Accepted Version Download (1MB) | Preview |
Abstract
The malicious use and widespread dissemination of deepfake pose a significant crisis of trust. Current deepfake detection models can generally recognize forgery images by training on a large dataset. However, the accuracy of detection models degrades significantly on images generated by new deepfake methods due to the difference in data distribution. To tackle this issue, we present a novel incremental learning framework that improves the generalization of deepfake detection models by continual learning from a small number of new samples. To cope with different data distributions, we propose to learn a domain-invariant representation based on supervised contrastive learning, preventing overfit to the insufficient new data. To mitigate catastrophic forgetting, we regularize our model in both feature-level and label-level based on a multi-perspective knowledge distillation approach. Finally, we propose to select both central and hard representative samples to update the replay set, which is beneficial for both domain-invariant representation learning and rehearsal-based knowledge preserving. We conduct extensive experiments on four benchmark datasets, obtaining the new state-of-the-art average forgetting rate of 7.01 and average accuracy of 85.49 on FF++, DFDC-P, DFD, and CDF2. Our code is released at \textcolorblue https://github.com/DeepFakeIL/DFIL.
| Type: | Proceedings paper |
|---|---|
| Title: | DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues |
| Event: | MM '23: The 31st ACM International Conference on Multimedia |
| Location: | Ottawa, Canada |
| Dates: | 29th October - 3rd November 2023 |
| ISBN-13: | 979-8-4007-0108-5 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3581783.3612377 |
| Publisher version: | http://dx.doi.org/10.1145/3581783.3612377 |
| 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/10200416 |
Archive Staff Only
 |
View Item |
