arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.11339cs.CV
收藏

人脸识别中的数据不确定性学习

Data Uncertainty Learning in Face Recognition

Megvii Inc.(旷视科技有限公司);University of Science and Technology of China(中国科学技术大学)

Jie Chang, Zhonghao Lan, Changmao Cheng, Yichen Wei

摘要:

建模数据的不确定性是很重要的噪声图像,但很少探索人脸识别。PFE的先驱工作,通过将每个人脸图像嵌入建模为高斯分布来考虑不确定性。这是相当有效的。但是,它使用来自现有模型的固定特征(高斯平均值)。它只估计方差,并依赖于一个临时的和昂贵的指标。因此,它不容易使用。目前还不清楚不确定性如何影响特征学习。这项工作将数据不确定性学习应用于人脸识别,首次同时学习特征(均值)和不确定性(方差)。提出了两种学习方法。它们易于使用,并且在具有挑战性的无约束场景中优于现有的确定性方法以及PFE。我们还提供了有见地的分析如何纳入不确定性估计有助于减少噪声样本的不利影响,影响特征学习。

英文摘要:

Modeling data uncertainty is important for noisy images, but seldom explored for face recognition. The pioneer work, PFE, considers uncertainty by modeling each face image embedding as a Gaussian distribution. It is quite effective. However, it uses fixed feature (mean of the Gaussian) from an existing model. It only estimates the variance and relies on an ad-hoc and costly metric. Thus, it is not easy to use. It is unclear how uncertainty affects feature learning. This work applies data uncertainty learning to face recognition, such that the feature (mean) and uncertainty (variance) are learnt simultaneously, for the first time. Two learning methods are proposed. They are easy to use and outperform existing deterministic methods as well as PFE on challenging unconstrained scenarios. We also provide insightful analysis on how incorporating uncertainty estimation helps reducing the adverse effects of noisy samples and affects the feature learning.

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。

↑