PulseAugur
实时 08:52:06
English(EN) Face-trace: Open-Set Attribution and Progressive Discovery of Synthetic Face Generators

Face-trace 管道支持开放集人脸合成器归因

研究人员开发了一个名为 Face-trace 的新管道,用于开放集人脸合成源归因。该方法可以识别合成人脸图像的生成器,即使在训练期间生成器未知或未见过。它结合了已知生成器分类、基于能量的分布外拒绝和聚类方法来发现新生成器。在 WILD 数据集上的实验表明,在闭集和开放集场景下均具有高准确率,并能够随着时间的推移渐进式地发现和分类未知生成器。 AI

影响 通过识别来自先前未见过的生成模型的合成人脸,增强了多媒体取证能力。

排序理由 研究论文,详细介绍了一种新的人脸合成器归因方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Face-trace 管道支持开放集人脸合成器归因

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Alessia Infantino, Claudio Schiavella, Irene Amerini ·

    Face-trace: Open-Set Attribution and Progressive Discovery of Synthetic Face Generators

    arXiv:2607.07545v1 Announce Type: new Abstract: Recent advances in generative Artificial Intelligence have made synthetic face images increasingly realistic, creating new challenges for multimedia forensics. Source attribution methods should not only identify the generator of an …

  2. arXiv cs.CV TIER_1 English(EN) · Irene Amerini ·

    Face-trace: Open-Set Attribution and Progressive Discovery of Synthetic Face Generators

    Recent advances in generative Artificial Intelligence have made synthetic face images increasingly realistic, creating new challenges for multimedia forensics. Source attribution methods should not only identify the generator of an image when the source is known, but also handle …