Generalizing Face Forgery Detection with High-frequency Features

TL;DR

This paper introduces a novel face forgery detection method that leverages high-frequency noise features and specialized modules to improve cross-database generalization over existing CNN-based detectors.

Contribution

It proposes a multi-scale high-frequency feature extraction and attention modules to enhance generalization in face forgery detection across different algorithms.

Findings

Outperforms existing methods in cross-database scenarios

Effectively captures high-frequency noise features

Demonstrates superior generalization on benchmark datasets

Abstract

Current face forgery detection methods achieve high accuracy under the within-database scenario where training and testing forgeries are synthesized by the same algorithm. However, few of them gain satisfying performance under the cross-database scenario where training and testing forgeries are synthesized by different algorithms. In this paper, we find that current CNN-based detectors tend to overfit to method-specific color textures and thus fail to generalize. Observing that image noises remove color textures and expose discrepancies between authentic and tampered regions, we propose to utilize the high-frequency noises for face forgery detection. We carefully devise three functional modules to take full advantage of the high-frequency features. The first is the multi-scale high-frequency feature extraction module that extracts high-frequency noises at multiple scales and composes a novel modality. The second is the residual-guided spatial attention module that guides the low-level RGB feature extractor to concentrate more on forgery traces from a new perspective. The last is the cross-modality attention module that leverages the correlation between the two complementary modalities to promote feature learning for each other. Comprehensive evaluations on several benchmark databases corroborate the superior generalization performance of our proposed method.