Generative Adversarial Ensemble Learning for Face Forensics
Generative Adversarial Ensemble Learning for Face Forensics
复制标题
DOI：
10.1109/access.2020.2968612
复制
发表时间：
2020-01-01
期刊：
影响因子：
3.9
通讯作者：
Bae, Seung-Hwan
中科院分区：
文献类型：
--
作者：
Baek, Jae-Yong;Yoo, Yong-Sang;Bae, Seung-Hwan
合成图像生成和操作方法的最新进展使我们能够生成接近真实图像的合成面部图像。另一方面，识别合成人脸图像的重要性越来越大，以保护个人隐私。尽管最近开发了一些基于深度学习的图像取证方法，但区分由最近的图像生成和操作方法（例如深度伪造、face2face 和面部交换）生成的合成图像仍然具有挑战性。为了解决这一挑战，我们提出了一种新颖的生成对抗性集成学习方法。我们基于对抗性学习训练多个判别和生成网络。然而，与传统的对抗性学习相比，我们的方法更注重提高辨别能力而不是图像生成能力。为此，我们通过集成来自不同两个判别器的输出来提高判别能力。此外，我们训练两个生成器以生成通用和硬合成图像。通过所有生成器和鉴别器的集成学习，我们通过使用生成的合成人脸图像来改进鉴别器，并通过传递鉴别器的组合反馈来改进生成器。在 FaceForensics 基准挑战中，我们通过比较最新的方法来彻底评估我们的方法。我们还提供了消融研究来证明我们方法的有效性和实用性。
The recent advance of synthetic image generation and manipulation methods allows us to generate synthetic face images close to real images. On the other hand, the importance of identifying the synthetic face images increases more and more to protect personal privacy from those. Although some deep learning-based image forensic methods have been developed recently, it is still challenging to distinguish synthetic images generated by recent image generation and manipulation methods such as the deep fake, face2face, and face swap. To resolve this challenge, we propose a novel generative adversarial ensemble learning method. We train multiple discriminative and generative networks based on the adversarial learning. Compared to the conventional adversarial learning, our method is however more focused on improving the discrimination ability rather than image generation one. To this end, we improve the discriminabilty by ensembling outputs from different two discriminators. In addition, we train two generators in order to generate general and hard synthetic images. By ensemble learning of all the generators and discriminators, we improve the discriminators by using the generated synthetic face images, and improve the generators by passing the combined feedback of the discriminators. On the FaceForensics benchmark challenge, we thoroughly evaluate our methods by comparing the recent methods. We also provide the ablation study to prove the effectiveness and usefulness of our method.