Searching for the Fakes: Efficient Neural Architecture Search for General Face Forgery Detection

TL;DR

This paper introduces an automated neural architecture search framework tailored for deepfake detection, enabling the design of effective models without manual effort, and demonstrates its competitive performance across datasets.

Contribution

The paper presents a novel NAS-based framework with a forgery-specific search space and a new performance metric for general face forgery detection.

Findings

Achieves competitive results compared to manually designed networks.

Demonstrates effectiveness in both in-dataset and cross-dataset scenarios.

Develops a forgery-oriented search space and a performance estimation metric.

Abstract

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.