arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.08754cs.MMcs.CV
收藏

学习在野外检测假人脸图像

Learning to Detect Fake Face Images in the Wild

National Pingtung University of Science and Technology(国立屏东科技大学);National United University(国立联合大学)

Chih-Chung Hsu, Chia-Yen Lee, Yi-Xiu Zhuang

摘要:

生成对抗网络(GAN)虽然可以用来生成真实感图像,但使用不当会带来隐患。例如,GAN可用于为特定人员和不适当事件生成篡改视频,从而创建对特定人员有害的图像,甚至可能影响该人员的人身安全。在本文中,我们将开发一种深度伪造检测器(DeepFD),以有效地检测计算机生成的图像。直接学习一个二元分类器是相对棘手的,因为很难找到共同的判别特征来判断不同GANs生成的假图像。为了解决这个缺点,我们采用对比损失来寻找由不同GANs生成的合成图像的典型特征,然后连接一个分类器来检测这样的计算机生成的图像。实验结果表明,所提出的DeepFD成功地检测到94.7%的虚假图像产生的几个国家的最先进的GANs。

英文摘要:

Although Generative Adversarial Network (GAN) can be used to generate the realistic image, improper use of these technologies brings hidden concerns. For example, GAN can be used to generate a tampered video for specific people and inappropriate events, creating images that are detrimental to a particular person, and may even affect that personal safety. In this paper, we will develop a deep forgery discriminator (DeepFD) to efficiently and effectively detect the computer-generated images. Directly learning a binary classifier is relatively tricky since it is hard to find the common discriminative features for judging the fake images generated from different GANs. To address this shortcoming, we adopt contrastive loss in seeking the typical features of the synthesized images generated by different GANs and follow by concatenating a classifier to detect such computer-generated images. Experimental results demonstrate that the proposed DeepFD successfully detected 94.7% fake images generated by several state-of-the-art GANs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑