핵심 개념
This paper proposes a novel Deepfake detection method that leverages a progressive disentanglement framework to separate identity information from artifact features in fake faces, leading to improved detection accuracy and generalization ability on unseen datasets.
Zhou, W., Luo, X., Zhang, Z., He, J., & Wu, X. (2024). Capture Artifacts via Progressive Disentangling and Purifying Blended Identities for Deepfake Detection. IEEE Transactions on Circuits and Systems for Video Technology.
This paper addresses the challenge of developing a Deepfake detection method with improved generalization ability, particularly on unseen datasets, by focusing on the accurate separation of identity information and artifact features in fake faces.