Searching for the Fakes: Efficient Neural Architecture Search for General Face Forgery Detection
This work addresses the need for efficient and generalizable face forgery detection methods, though it is incremental as it applies NAS to an existing domain.
The paper tackles the problem of labor-intensive manual design in face forgery detection by developing an end-to-end neural architecture search (NAS) framework that automatically designs network architectures, achieving competitive performance in both in-dataset and cross-dataset scenarios.
As the saying goes, "seeing is believing". However, with the development of digital face editing tools, we can no longer trust what we can see. Although face forgery detection has made promising progress, most current methods are designed manually by human experts, which is labor-consuming. In this paper, we develop an end-to-end framework based on neural architecture search (NAS) for deepfake detection, which can automatically design network architectures without human intervention. First, a forgery-oriented search space is created to choose appropriate operations for this task. Second, we propose a novel performance estimation metric, which guides the search process to select more general models. The cross-dataset search is also considered to develop more general architectures. Eventually, we connect the cells in a cascaded pyramid way for final forgery classification. Compared with state-of-the-art networks artificially designed, our method achieves competitive performance in both in-dataset and cross-dataset scenarios.