Decoupling Forgery Semantics for Generalizable Deepfake Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ye, Wei, He, Xinan, Ding, Feng
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910719389204480
author Ye, Wei
He, Xinan
Ding, Feng
author_facet Ye, Wei
He, Xinan
Ding, Feng
contents In this paper, we propose a novel method for detecting DeepFakes, enhancing the generalization of detection through semantic decoupling. There are now multiple DeepFake forgery technologies that not only possess unique forgery semantics but may also share common forgery semantics. The unique forgery semantics and irrelevant content semantics may promote over-fitting and hamper generalization for DeepFake detectors. For our proposed method, after decoupling, the common forgery semantics could be extracted from DeepFakes, and subsequently be employed for developing the generalizability of DeepFake detectors. Also, to pursue additional generalizability, we designed an adaptive high-pass module and a two-stage training strategy to improve the independence of decoupled semantics. Evaluation on FF++, Celeb-DF, DFD, and DFDC datasets showcases our method's excellent detection and generalization performance. Code is available at: https://github.com/leaffeall/DFS-GDD.
format Preprint
id arxiv_https___arxiv_org_abs_2406_09739
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Decoupling Forgery Semantics for Generalizable Deepfake Detection
Ye, Wei
He, Xinan
Ding, Feng
Computer Vision and Pattern Recognition
In this paper, we propose a novel method for detecting DeepFakes, enhancing the generalization of detection through semantic decoupling. There are now multiple DeepFake forgery technologies that not only possess unique forgery semantics but may also share common forgery semantics. The unique forgery semantics and irrelevant content semantics may promote over-fitting and hamper generalization for DeepFake detectors. For our proposed method, after decoupling, the common forgery semantics could be extracted from DeepFakes, and subsequently be employed for developing the generalizability of DeepFake detectors. Also, to pursue additional generalizability, we designed an adaptive high-pass module and a two-stage training strategy to improve the independence of decoupled semantics. Evaluation on FF++, Celeb-DF, DFD, and DFDC datasets showcases our method's excellent detection and generalization performance. Code is available at: https://github.com/leaffeall/DFS-GDD.
title Decoupling Forgery Semantics for Generalizable Deepfake Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.09739