期刊
COMPUTER VISION AND IMAGE UNDERSTANDING
卷 226, 期 -, 页码 -出版社
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.cviu.2022.103587
关键词
Deepfake detection; Data augmentation; Face forgery detection; Structured forgery clues
This paper investigates the importance of structured forgery clues for fake face image detection and proposes a new data augmentation framework called Mining Structured Features (MSF) to improve the performance of CNN-based detectors. By generating a position-sensitive artifact map and dynamically erasing regions during training, MSF expands the attention range of the detector and fully mines the structured features from global images.
For fake face image detection, most existing detectors exploit local artifacts, ignoring the mining of structured forgery clues existed in global images, which greatly constrains detection performance. In this work, we verify the importance of structured forgery clues for fake face image detection, and present a new data augmentation framework called Mining Structured Features (MSF) to promote the convolutional neural network (CNN) based detector. Specifically, MSF generates a position-sensitive artifact map, which is exploited to divide a candidate face image into strong correlation (SC) and weak correlation (WC) regions. By dynamically erasing some positions in SC and WC regions during the training process, MSF can promote the robustness of the detector to the above regions. In essence, MSF expands the attention range of the detector and fully mines the structured features from global images. MSF plays an auxiliary role, which can be seamlessly integrated into existing CNN-based detectors for end-to-end training. Extensive experimental results on four public datasets including HFFD, FF++, DFDC and Celeb-DF show that the detectors trained with the guidance of MSF can mine more useful clues distributed in fake face images to improve detection accuracies, achieving better results than state-of-the-art works. Our code will be available at https://github.com/EricGzq/MSF.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据