Dual Contrastive Learning for General Face Forgery Detection

TL;DR

This paper introduces Dual Contrastive Learning (DCL), a novel framework for face forgery detection that enhances generalization by learning discriminative features through inter- and intra-instance contrastive strategies.

Contribution

The paper proposes a new contrastive learning framework with inter- and intra-instance strategies specifically designed for robust face forgery detection.

Findings

Outperforms state-of-the-art methods on multiple datasets

Demonstrates strong generalization to unseen forgery techniques

Effectively captures local content inconsistencies in forged faces

Abstract

With various facial manipulation techniques arising, face forgery detection has drawn growing attention due to security concerns. Previous works always formulate face forgery detection as a classification problem based on cross-entropy loss, which emphasizes category-level differences rather than the essential discrepancies between real and fake faces, limiting model generalization in unseen domains. To address this issue, we propose a novel face forgery detection framework, named Dual Contrastive Learning (DCL), which specially constructs positive and negative paired data and performs designed contrastive learning at different granularities to learn generalized feature representation. Concretely, combined with the hard sample selection strategy, Inter-Instance Contrastive Learning (Inter-ICL) is first proposed to promote task-related discriminative features learning by especially constructing instance pairs. Moreover, to further explore the essential discrepancies, Intra-Instance Contrastive Learning (Intra-ICL) is introduced to focus on the local content inconsistencies prevalent in the forged faces by constructing local-region pairs inside instances. Extensive experiments and visualizations on several datasets demonstrate the generalization of our method against the state-of-the-art competitors.