A Triple Complementary Stream Network based on forgery feature enhancement and coupling for universal face forgery localization

Abstract

Existing face forgery detection methods are easily attacked by unknown facial operations and forgery techniques, and cannot accurately locate the forgery area. To solve this problem, we propose a Triple Complementary Stream Network (TCSN) for universal face forgery localization. TCSN innovatively explores universal forgery clues from the depth stream, RGB stream, and frequency stream. First, we construct a feature enhancement module that employs the features of the complementary streams to suppress semantic features and capture the universal forgery features. Subsequently, we design a dynamic affinity graph feature coupling module based on affinity propagation. This module utilizes the correlation between different stream forgery features to promote the transfer of shared and specific features across streams. TCSN achieved state-of-the-art performance on three face forgery localization datasets and demonstrated strong generalization ability. Our code and datasets are available on https://github.com/hywang02/TCSN.