WATCHER: Wavelet-Guided Texture-Content Hierarchical Relation Learning for Deepfake Detection

Breathtaking advances in face forgery techniques produce visually untraceable deepfake videos, thus potential malicious abuse of these techniques has sparked great concerns. Existing deepfake detectors primarily focus on specific forgery patterns with global features extracted by CNN backbones for f...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computer vision 2024-10, Vol.132 (10), p.4746-4767
Main Authors: Wang, Yuan, Chen, Chen, Zhang, Ning, Hu, Xiyuan
Format: Article
Language:English
Subjects:
Artificial Intelligence
Attention
Computer Imaging
Computer Science
Counterfeit
Deception
Deepfake
Detection
Feature extraction
Forgery
Image Processing and Computer Vision
Learning
Modules
Pattern Recognition
Pattern Recognition and Graphics
Special Issue on Biometrics Security and Privacy
Texture
Vision
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Breathtaking advances in face forgery techniques produce visually untraceable deepfake videos, thus potential malicious abuse of these techniques has sparked great concerns. Existing deepfake detectors primarily focus on specific forgery patterns with global features extracted by CNN backbones for forgery detection. Due to inadequate exploration of content and texture features, they often suffer from overfitting method-specific forged regions, thus exhibiting limited generalization to increasingly realistic forgeries. In this paper, we propose a Wa velet-guided T exture- C ontent H i E rarchical R elation (WATCHER) Learning framework to delve deeper into the relation-aware texture-content features. Specifically, we propose a Wavelet-guided AutoEncoder scheme to retrieve the general visual representation, which is aware of high-frequency details for understanding forgeries. To further excavate fine-grained counterfeit clues, a Texture-Content Attention Maps Learning module is presented to enrich the contextual information of content and texture features via multi-level attention maps in a hierarchical learning protocol. Finally, we propose a Progressive Multi-domain Feature Interaction module in pursuit to perform semantic reasoning on relationship-enhanced texture-content forgery features. Extensive experiments on popular benchmark datasets substantiate the superiority of our WATCHER model, consistently trumping state-of-the-art methods by a significant margin.
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-024-02116-5