Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learning

TL;DR

This paper introduces a progressive enhancement learning framework that effectively exploits both RGB and fine-grained frequency clues to improve face forgery detection accuracy, addressing limitations of coarse-grained frequency analysis.

Contribution

The paper proposes a novel two-branch network with self- and mutual-enhancement modules for fine-grained face forgery clue extraction, outperforming existing methods.

Findings

Outperforms state-of-the-art face forgery detection methods.

Effectively captures fine-grained forgery traces in both RGB and frequency domains.

Demonstrates robustness across multiple datasets.

Abstract

With the rapid development of facial forgery techniques, forgery detection has attracted more and more attention due to security concerns. Existing approaches attempt to use frequency information to mine subtle artifacts under high-quality forged faces. However, the exploitation of frequency information is coarse-grained, and more importantly, their vanilla learning process struggles to extract fine-grained forgery traces. To address this issue, we propose a progressive enhancement learning framework to exploit both the RGB and fine-grained frequency clues. Specifically, we perform a fine-grained decomposition of RGB images to completely decouple the real and fake traces in the frequency space. Subsequently, we propose a progressive enhancement learning framework based on a two-branch network, combined with self-enhancement and mutual-enhancement modules. The self-enhancement module captures the traces in different input spaces based on spatial noise enhancement and channel attention. The Mutual-enhancement module concurrently enhances RGB and frequency features by communicating in the shared spatial dimension. The progressive enhancement process facilitates the learning of discriminative features with fine-grained face forgery clues. Extensive experiments on several datasets show that our method outperforms the state-of-the-art face forgery detection methods.