FakeLocator: Robust Localization of GAN-Based Face Manipulations

计算机科学 人工智能 增采样 面子(社会学概念) 计算机视觉 模式识别(心理学) 稳健性(进化) 聚类分析 图像(数学) 社会科学 生物化学 化学 社会学 基因
作者
Yihao Huang,Felix Juefei-Xu,Qing Guo,Yang Liu,Geguang Pu
出处
期刊:IEEE Transactions on Information Forensics and Security [Institute of Electrical and Electronics Engineers]
卷期号:17: 2657-2672 被引量:66
标识
DOI:10.1109/tifs.2022.3141262
摘要

Full face synthesis and partial face manipulation by virtue of the generative adversarial networks (GANs) and its variants have raised wide public concerns. In the multi-media forensics area, detecting and ultimately locating the image forgery has become an imperative task. In this work, we investigate the architecture of existing GAN-based face manipulation methods and observe that the imperfection of upsampling methods therewithin could be served as an important asset for GAN-synthesized fake image detection and forgery localization. Based on this basic observation, we have proposed a novel approach, termed FakeLocator, to obtain high localization accuracy, at full resolution, on manipulated facial images. To the best of our knowledge, this is the very first attempt to solve the GAN-based fake localization problem with a gray-scale fakeness map that preserves more information of fake regions. To improve the universality of FakeLocator across multifarious facial attributes, we introduce an attention mechanism to guide the training of the model. To improve the universality of FakeLocator across different DeepFake methods, we propose partial data augmentation and single sample clustering on the training images. Experimental results on popular FaceForensics++, DFFD datasets and seven different state-of-the-art GAN-based face generation methods have shown the effectiveness of our method. Compared with the baselines, our method performs better on various metrics. Moreover, the proposed method is robust against various real-world facial image degradations such as JPEG compression, low-resolution, noise, and blur.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
wys3712完成签到,获得积分20
刚刚
靖哥哥发布了新的文献求助10
1秒前
1秒前
1秒前
1秒前
1秒前
缓慢凝梦完成签到,获得积分10
1秒前
1秒前
情怀应助Veronica采纳,获得10
2秒前
2秒前
2秒前
123发布了新的文献求助10
2秒前
爆米花应助鲤鱼水池采纳,获得10
2秒前
ljymedical发布了新的文献求助10
3秒前
yyyy完成签到 ,获得积分10
3秒前
LiYipeiiiiOvO发布了新的文献求助10
3秒前
长情完成签到,获得积分10
3秒前
落冰花发布了新的文献求助10
3秒前
3秒前
3秒前
4秒前
4秒前
4秒前
感动的听荷完成签到,获得积分10
4秒前
5秒前
5秒前
5秒前
5秒前
无私的黄豆完成签到 ,获得积分10
5秒前
leeteukxx发布了新的文献求助10
5秒前
6秒前
这样很OK发布了新的文献求助10
6秒前
6秒前
cheng完成签到,获得积分10
6秒前
呼啦啦完成签到,获得积分10
6秒前
自觉孤云发布了新的文献求助20
7秒前
Akim应助oliver采纳,获得10
8秒前
甜甜的如波关注了科研通微信公众号
8秒前
科研通AI6.4应助leonxp采纳,获得10
8秒前
王鹏斐完成签到,获得积分10
8秒前
高分求助中
Principles of Economics, 11th Edition 10000
University Physics with Modern Physics, 16th edition 10000
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Matrix Methods in Data Mining and Pattern Recognition 510
Social Skills Improvement System-Rating Scales--Chinese Version 500
Dynamische Polarisation von H-1 und B-11 in (CH-3)-3NBH-3 500
CLSI M07 2024 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7248548
求助须知:如何正确求助?哪些是违规求助? 8871390
关于积分的说明 18718058
捐赠科研通 6927750
什么是DOI,文献DOI怎么找? 3198424
关于科研通互助平台的介绍 2373952
邀请新用户注册赠送积分活动 2173173