Attention Consistency Refined Masked Frequency Forgery Representation for Generalizing Face Forgery Detection

TL;DR

This paper introduces a novel face forgery detection model that enhances generalization to unseen forgeries by refining frequency-based cues and enforcing attention consistency, achieving superior results across multiple datasets.

Contribution

The paper proposes the ACMF model combining masked frequency cues and attention consistency to improve forgery detection generalization to unseen artifact types.

Findings

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

Enhances robustness to unseen forgery artifacts

Improves focus consistency in detection networks

Abstract

Due to the successful development of deep image generation technology, visual data forgery detection would play a more important role in social and economic security. Existing forgery detection methods suffer from unsatisfactory generalization ability to determine the authenticity in the unseen domain. In this paper, we propose a novel Attention Consistency Refined masked frequency forgery representation model toward generalizing face forgery detection algorithm (ACMF). Most forgery technologies always bring in high-frequency aware cues, which make it easy to distinguish source authenticity but difficult to generalize to unseen artifact types. The masked frequency forgery representation module is designed to explore robust forgery cues by randomly discarding high-frequency information. In addition, we find that the forgery attention map inconsistency through the detection network could affect the generalizability. Thus, the forgery attention consistency is introduced to force detectors to focus on similar attention regions for better generalization ability. Experiment results on several public face forgery datasets (FaceForensic++, DFD, Celeb-DF, and WDF datasets) demonstrate the superior performance of the proposed method compared with the state-of-the-art methods.