English

Self-supervised Transformer for Deepfake Detection

Computer Vision and Pattern Recognition 2022-03-03 v1

Abstract

The fast evolution and widespread of deepfake techniques in real-world scenarios require stronger generalization abilities of face forgery detectors. Some works capture the features that are unrelated to method-specific artifacts, such as clues of blending boundary, accumulated up-sampling, to strengthen the generalization ability. However, the effectiveness of these methods can be easily corrupted by post-processing operations such as compression. Inspired by transfer learning, neural networks pre-trained on other large-scale face-related tasks may provide useful features for deepfake detection. For example, lip movement has been proved to be a kind of robust and good-transferring highlevel semantic feature, which can be learned from the lipreading task. However, the existing method pre-trains the lip feature extraction model in a supervised manner, which requires plenty of human resources in data annotation and increases the difficulty of obtaining training data. In this paper, we propose a self-supervised transformer based audio-visual contrastive learning method. The proposed method learns mouth motion representations by encouraging the paired video and audio representations to be close while unpaired ones to be diverse. After pre-training with our method, the model will then be partially fine-tuned for deepfake detection task. Extensive experiments show that our self-supervised method performs comparably or even better than the supervised pre-training counterpart.

Keywords

Cite

@article{arxiv.2203.01265,
  title  = {Self-supervised Transformer for Deepfake Detection},
  author = {Hanqing Zhao and Wenbo Zhou and Dongdong Chen and Weiming Zhang and Nenghai Yu},
  journal= {arXiv preprint arXiv:2203.01265},
  year   = {2022}
}
R2 v1 2026-06-24T09:59:39.814Z