DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learning
This addresses the need for deepfake detection without labeled data, offering a practical solution for security applications, though it is incremental as it builds on existing contrastive learning approaches.
The paper tackles the problem of face deepfake detection by proposing an unsupervised contrastive learning method, achieving comparable performance to state-of-the-art supervised techniques in both intra- and inter-dataset settings.
Face deepfake detection has seen impressive results recently. Nearly all existing deep learning techniques for face deepfake detection are fully supervised and require labels during training. In this paper, we design a novel deepfake detection method via unsupervised contrastive learning. We first generate two different transformed versions of an image and feed them into two sequential sub-networks, i.e., an encoder and a projection head. The unsupervised training is achieved by maximizing the correspondence degree of the outputs of the projection head. To evaluate the detection performance of our unsupervised method, we further use the unsupervised features to train an efficient linear classification network. Extensive experiments show that our unsupervised learning method enables comparable detection performance to state-of-the-art supervised techniques, in both the intra- and inter-dataset settings. We also conduct ablation studies for our method.