Back to Search Start Over

Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection

Authors :
Cui, Xinjie
Li, Yuezun
Luo, Ao
Zhou, Jiaran
Dong, Junyu
Publication Year :
2024

Abstract

We describe the Forensics Adapter, an adapter network designed to transform CLIP into an effective and generalizable face forgery detector. Although CLIP is highly versatile, adapting it for face forgery detection is non-trivial as forgery-related knowledge is entangled with a wide range of unrelated knowledge. Existing methods treat CLIP merely as a feature extractor, lacking task-specific adaptation, which limits their effectiveness. To address this, we introduce an adapter to learn face forgery traces -- the blending boundaries unique to forged faces, guided by task-specific objectives. Then we enhance the CLIP visual tokens with a dedicated interaction strategy that communicates knowledge across CLIP and the adapter. Since the adapter is alongside CLIP, its versatility is highly retained, naturally ensuring strong generalizability in face forgery detection. With only $\bm{5.7M}$ trainable parameters, our method achieves a significant performance boost, improving by approximately $\bm{7\%}$ on average across five standard datasets. We believe the proposed method can serve as a baseline for future CLIP-based face forgery detection methods.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2411.19715
Document Type :
Working Paper