arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.10079cs.CV
收藏

使用合成人脸数据的人脸识别

Face Recognition Using Synthetic Face Data

Datagen(Datagen公司)

Omer Granoviter, Alexey Gruzdev, Vladimir Loginov, Max Kogan, Orly Zvitia

AI总结:

本文提出利用计算机图形学管线生成的合成人脸数据训练人脸识别模型,在多个基准上取得媲美真实数据训练的效果,并探究了类内方差因素及人脸部件变化对模型性能的影响。

摘要:

在深度学习应用于人脸识别的领域,获取大规模、高质量的数据集对于获得精确且可靠的结果至关重要。然而,收集大量高质量的真实数据面临着时间限制、财务负担和隐私问题等障碍。此外,现有的数据集经常受到种族偏见和标注不准确的影响。在本文中,我们强调了合成数据的有前途的应用,该合成数据是通过我们的计算机图形学管线渲染数字人脸生成的,在多个基准数据集上基于合成数据取得了与最先进方法相媲美的结果。通过微调模型,我们获得的结果可与使用数十万张真实图像训练时取得的结果相媲美(在 LFW [1] 上为 98.7%)。我们进一步研究了添加类内方差因素(例如,化妆、配饰、发型)对模型性能的贡献。最后,我们利用我们平台中的细粒度控制能力,揭示了预训练人脸识别模型对人脸特定部分交替变化的敏感性。

英文摘要:

In the field of deep learning applied to face recognition, securing large-scale, high-quality datasets is vital for attaining precise and reliable results. However, amassing significant volumes of high-quality real data faces hurdles such as time limitations, financial burdens, and privacy issues. Furthermore, prevalent datasets are often impaired by racial biases and annotation inaccuracies. In this paper, we underscore the promising application of synthetic data, generated through rendering digital faces via our computer graphics pipeline, in achieving competitive results with the state-of-the-art on synthetic data across multiple benchmark datasets. By finetuning the model,we obtain results that rival those achieved when training with hundreds of thousands of real images (98.7% on LFW [1]). We further investigate the contribution of adding intra-class variance factors (e.g., makeup, accessories, haircuts) on model performance. Finally, we reveal the sensitivity of pre-trained face recognition models to alternating specific parts of the face by leveraging the granular control capability in our platform.

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。

↑