论文标题
通过每个受试者的对抗数据增强探索面部识别中的种族偏见
Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation
论文作者
论文摘要
尽管面部识别应用在我们的日常生活中越来越普遍，但该领域的领先方法仍然遭受绩效偏见，损害了社会内一些种族特征。在这项研究中，我们提出了一种新型的对抗性数据增强方法，旨在通过使用图像到图像转换来转移敏感的种族特征面部特征，以使数据集平衡以人为对象的水平。我们的目的是通过在不同的种族领域转换面部图像来自动构建合成的数据集，同时仍然保留与身份相关的特征，以便随后在确定主题身份的情况下与种族依赖的特征无关紧要。我们在三种重要的面部识别变体上构建实验：在常见的卷积神经网络主链上软磁性，cosce和Arcface损失。在并排比较中，我们表明了我们提出的技术可以通过降低最初不平衡培训数据集中（种族）少数群体的识别绩效产生积极影响，这是通过降低绩效的预赛差异。
Whilst face recognition applications are becoming increasingly prevalent within our daily lives, leading approaches in the field still suffer from performance bias to the detriment of some racial profiles within society. In this study, we propose a novel adversarial derived data augmentation methodology that aims to enable dataset balance at a per-subject level via the use of image-to-image transformation for the transfer of sensitive racial characteristic facial features. Our aim is to automatically construct a synthesised dataset by transforming facial images across varying racial domains, while still preserving identity-related features, such that racially dependant features subsequently become irrelevant within the determination of subject identity. We construct our experiments on three significant face recognition variants: Softmax, CosFace and ArcFace loss over a common convolutional neural network backbone. In a side-by-side comparison, we show the positive impact our proposed technique can have on the recognition performance for (racial) minority groups within an originally imbalanced training dataset by reducing the pre-race variance in performance.
