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

doi:10.1007/s11263-024-02116-5

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室 > 医疗机器人

	WATCHER: Wavelet-Guided Texture-Content Hierarchical Relation Learning for Deepfake Detection
	Wang, Yuan 4,5,6; Chen, Chen 3; Zhang, Ning 2; Hu, Xiyuan 1
刊名	INTERNATIONAL JOURNAL OF COMPUTER VISION
	2024-05-23
页码	22
关键词	Face forgery detection Texture features Attention maps learning Relation-aware feature fusion
ISSN号	0920-5691
DOI	10.1007/s11263-024-02116-5
通讯作者	Hu, Xiyuan(huxiyuan@bjut.edu.cn)
英文摘要	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 Wavelet-guided Texture-Content HiErarchical Relation (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.
资助项目	Key Technologies Research and Development Program[2021YFF0602101] ; National Key R &D Program of China[62172227] ; National Natural Science Foundation of China
WOS关键词	IMAGE DECOMPOSITION ; SCALE
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:001230131200003
资助机构	Key Technologies Research and Development Program ; National Key R &D Program of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/58436]
专题	多模态人工智能系统全国重点实验室_医疗机器人
通讯作者	Hu, Xiyuan
作者单位	1.Beijing Univ Technol, Faulty Informat Technol, Beijing 100124, Peoples R China 2.Minist Publ Secur, Inst Forens Sci, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automation, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 4.Beijing Natl Res Ctr Informat Sci & Technol BNRist, Beijing 100084, Peoples R China 5.Tsinghua Univ, Dept Elect Engn, Beijing 100083, Peoples R China 6.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wang, Yuan,Chen, Chen,Zhang, Ning,et al. WATCHER: Wavelet-Guided Texture-Content Hierarchical Relation Learning for Deepfake Detection[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2024:22.
APA	Wang, Yuan,Chen, Chen,Zhang, Ning,&Hu, Xiyuan.(2024).WATCHER: Wavelet-Guided Texture-Content Hierarchical Relation Learning for Deepfake Detection.INTERNATIONAL JOURNAL OF COMPUTER VISION,22.
MLA	Wang, Yuan,et al."WATCHER: Wavelet-Guided Texture-Content Hierarchical Relation Learning for Deepfake Detection".INTERNATIONAL JOURNAL OF COMPUTER VISION (2024):22.