Domain General Face Forgery Detection by Learning to Weight

Authors

  • Ke Sun Media Analytics and Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University, 361005, China
  • Hong Liu National Institute of Informatics, Japan
  • Qixiang Ye University of Chinese Academy of Sciences, China
  • Yue Gao Tsinghua University, China
  • Jianzhuang Liu Noah's Ark Lab, Huawei Technologies, China
  • Ling Shao Inception Institute of Artificial Intelligence, Abu Dhabi, UAE
  • Rongrong Ji Media Analytics and Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University, 361005, China Institute of Artificial Intelligence, Xiamen University

Keywords:

Object Detection & Categorization

Abstract

In this paper, we propose a domain-general model, termed learning-to-weight (LTW), that guarantees face detection performance across multiple domains, particularly the target domains that are never seen before. However, various face forgery methods cause complex and biased data distributions, making it challenging to detect fake faces in unseen domains. We argue that different faces contribute differently to a detection model trained on multiple domains, making the model likely to fit domain-specific biases. As such, we propose the LTW approach based on the meta-weight learning algorithm, which configures different weights for face images from different domains. The LTW network can balance the model's generalizability across multiple domains. Then, the meta-optimization calibrates the source domain's gradient enabling more discriminative features to be learned. The detection ability of the network is further improved by introducing an intra-class compact loss. Extensive experiments on several commonly used deepfake datasets to demonstrate the effectiveness of our method in detecting synthetic faces. Code and supplemental material are available at https://github.com/skJack/LTW.

Downloads

Published

2021-05-18

How to Cite

Sun, K., Liu, H., Ye, Q., Gao, Y., Liu, J., Shao, L., & Ji, R. (2021). Domain General Face Forgery Detection by Learning to Weight. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 2638-2646. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16367

Issue

Section

AAAI Technical Track on Computer Vision II