来自今天的爱可可AI前沿推介

[CV] A Dataless FaceSwap Detection Approach Using Synthetic Images

A Jain, N Memon, J Togelius
[New York University]

基于合成图像的无数据换脸检测方法

简介:提出一种无需真实数据、用合成图像检测换脸的方法。这种无数据和隐私感知方法被证明可以与传统的基于真实数据的模型相竞争,经过少量微调,甚至可以超过它们。此外,该方法偏差较小,有助于减少记忆和隐私问题。该方法用不同种族、性别和年龄组进行了测试,结果显示合成数据有多方面优势。

摘要:过去几年中,用于创造"深度假象(Deepfakes)"的换脸技术有了很大的进步,现在可以创造出真实的人脸操纵。目前用于检测Deepfakes的深度学习算法已经显示出有希望的结果,然而,它们需要大量的训练数据,且偏向于某个特定种族。本文提出一种Deepfakes检测方法,通过用StyleGAN3合成的数据,消除了对真实数据的需求。不仅与使用真实数据的传统训练方法表现相当,而且在使用少量真实数据进行微调时,会显示出更好的泛化能力。此外,也减少了由人脸图像数据集产生的偏差,这些数据集可能有来自特定种族的稀疏数据。

Face swapping technology used to create "Deepfakes" has advanced significantly over the past few years and now enables us to create realistic facial manipulations. Current deep learning algorithms to detect deepfakes have shown promising results, however, they require large amounts of training data, and as we show they are biased towards a particular ethnicity. We propose a deepfake detection methodology that eliminates the need for any real data by making use of synthetically generated data using StyleGAN3. This not only performs at par with the traditional training methodology of using real data but it shows better generalization capabilities when finetuned with a small amount of real data. Furthermore, this also reduces biases created by facial image datasets that might have sparse data from particular ethnicities.

论文链接:https://arxiv.org/abs/2212.02571

图片

图片

图片

图片

内容中包含的图片若涉及版权问题,请及时与我们联系删除