Papers
arxiv:2103.16076

Face Forensics in the Wild

Published on Mar 30, 2021
Authors:
,
,
,

Abstract

A large-scale dataset and novel algorithm for multi-person face forgery detection are presented, achieving superior performance in both classification and localization tasks.

AI-generated summary

On existing public benchmarks, face forgery detection techniques have achieved great success. However, when used in multi-person videos, which often contain many people active in the scene with only a small subset having been manipulated, their performance remains far from being satisfactory. To take face forgery detection to a new level, we construct a novel large-scale dataset, called FFIW-10K, which comprises 10,000 high-quality forgery videos, with an average of three human faces in each frame. The manipulation procedure is fully automatic, controlled by a domain-adversarial quality assessment network, making our dataset highly scalable with low human cost. In addition, we propose a novel algorithm to tackle the task of multi-person face forgery detection. Supervised by only video-level label, the algorithm explores multiple instance learning and learns to automatically attend to tampered faces. Our algorithm outperforms representative approaches for both forgery classification and localization on FFIW-10K, and also shows high generalization ability on existing benchmarks. We hope that our dataset and study will help the community to explore this new field in more depth.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2103.16076 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2103.16076 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2103.16076 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.