Face Forensics in the Wild

TL;DR

This paper introduces a large-scale dataset FFIW-10K for multi-person face forgery detection and proposes a novel attention-based algorithm that outperforms existing methods and generalizes well across benchmarks.

Contribution

The paper presents a new scalable dataset FFIW-10K and a novel multi-person face forgery detection algorithm using multiple instance learning and attention mechanisms.

Findings

The algorithm outperforms existing methods on FFIW-10K.

High generalization ability on other benchmarks.

The dataset enables more in-depth exploration of multi-person forgery detection.

Abstract

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.