Deep learning has catalysed progress in tasks such as face recognition and analysis, leading to a quick integration of technological solutions in multiple layers of our society. While such systems have proven to be accurate by standard evaluation metrics and benchmarks, a surge of work has recently exposed the demographic bias that such algorithms exhibit–highlighting that accuracy does not entail fairness. Clearly, deploying biased systems under real-world settings can have grave consequences for affected populations. Indeed, learning methods are prone to inheriting, or even amplifying the bias present in a training set, manifested by uneven representation across demographic groups. In facial datasets, this particularly relates to attributes such as skin tone, gender, and age. In this work, we address the problem of mitigating bias in facial datasets by data augmentation. We propose a multi-attribute framework that can successfully transfer complex, multi-scale facial patterns even if these belong to underrepresented groups in the training set. This is achieved by relaxing the rigid dependence on a single attribute label, and further introducing a tensor-based mixing structure that captures multiplicative interactions between attributes in a multilinear fashion. We evaluate our method with an extensive set of qualitative and quantitative experiments on several datasets, with rigorous comparisons to state-of-the-art methods. We find that the proposed framework can successfully mitigate dataset bias, as evinced by extensive evaluations on established diversity metrics, while significantly improving fairness metrics such as equality of opportunity.

深度学习促进了面部识别和分析等任务的进展，从而导致技术解决方案在我们社会的各个层面快速整合。尽管通过标准评估指标和基准已证明此类系统是准确的，但最近的工作激增暴露了此类算法所表现出的人口统计学偏差–强调了准确性并不意味着公平。显然，在实际环境中部署有偏见的系统可能会对受影响的人群造成严重后果。确实，学习方法易于继承甚至放大训练集中存在的偏见，这在不同人群之间的代表性不均表现出来。在面部数据集中，这尤其涉及诸如以下的属性：肤色，性别和年龄。在这项工作中，我们解决了通过数据增强来缓解面部数据集中偏差的问题。我们提出了一个多属性框架，该框架甚至可以成功转移复杂的多尺度面部图案如果它们属于训练集中代表性不足的组。这是通过放宽对单个属性标签的严格依赖性，并进一步引入基于张量的混合结构来实现的，该结构以多线性方式捕获属性之间的乘法相互作用。我们通过对多个数据集进行广泛的定性和定量实验来评估我们的方法，并与最先进的方法进行严格的比较。我们发现，所提出的框架可以成功缓解数据集偏差，正如对既定多样性指标进行的广泛评估所证明的那样，同时可以显着提高公平性指标，例如机会均等。