Discrepancy-Guided Reconstruction Learning for Image Forgery Detection

TL;DR

This paper introduces a new image forgery detection approach that combines discrepancy-guided encoding and reconstruction learning to improve detection accuracy and generalization across diverse forgery types.

Contribution

The paper presents a novel discrepancy-guided encoder and a double-head reconstruction module that enhance forgery-sensitive pattern extraction and genuine pattern reinforcement, outperforming existing methods.

Findings

Outperforms state-of-the-art on four datasets

Improves detection of unknown forgery patterns

Enhances generalization across diverse forgeries

Abstract

In this paper, we propose a novel image forgery detection paradigm for boosting the model learning capacity on both forgery-sensitive and genuine compact visual patterns. Compared to the existing methods that only focus on the discrepant-specific patterns (\eg, noises, textures, and frequencies), our method has a greater generalization. Specifically, we first propose a Discrepancy-Guided Encoder (DisGE) to extract forgery-sensitive visual patterns. DisGE consists of two branches, where the mainstream backbone branch is used to extract general semantic features, and the accessorial discrepant external attention branch is used to extract explicit forgery cues. Besides, a Double-Head Reconstruction (DouHR) module is proposed to enhance genuine compact visual patterns in different granular spaces. Under DouHR, we further introduce a Discrepancy-Aggregation Detector (DisAD) to aggregate these genuine compact visual patterns, such that the forgery detection capability on unknown patterns can be improved. Extensive experimental results on four challenging datasets validate the effectiveness of our proposed method against state-of-the-art competitors.