What is the best way to learn a universal face representation? Recent work on Deep Learning in the area of face analysis has focused on supervised learning for specific tasks of interest (e.g. face recognition, facial landmark localization etc.) but has overlooked the overarching question of how to find a facial representation that can be readily adapted to several facial analysis tasks and datasets. To this end, we make the following 4 contributions: (a) we introduce, for the first time, a comprehensive evaluation benchmark for facial representation learning consisting of 5 important face analysis tasks. (b) We systematically investigate two ways of large-scale representation learning applied to faces: supervised and unsupervised pre-training. Importantly, we focus our evaluations on the case of few-shot facial learning. (c) We investigate important properties of the training datasets including their size and quality (labelled, unlabelled or even uncurated). (d) To draw our conclusions, we conducted a very large number of experiments. Our main two findings are: (1) Unsupervised pre-training on completely in-the-wild, uncurated data provides consistent and, in some cases, significant accuracy improvements for all facial tasks considered. (2) Many existing facial video datasets seem to have a large amount of redundancy. We will release code, and pre-trained models to facilitate future research.
翻译:· 最近关于面部分析领域深度学习的工作侧重于对特定感兴趣任务(如面部识别、面部标志性定位等)的监督性学习,但忽视了如何找到面部代表这一可以随时适应面部分析任务和数据集的总括性问题。 为此,我们作出以下4项贡献:(a) 我们首次为面部代表学习引入一个全面的评价基准,其中包括5项重要面部分析任务。 (b) 我们系统地调查适用于面部的大规模代表性学习的两种方法:受监督和不受监督的训练前阶段。 重要的是,我们集中评价少数面部学习的案例。 (c) 我们调查培训数据集的重要属性,包括其大小和质量(标签、未贴标签或甚至未贴上标签)。 (d) 为了得出我们的结论,我们进行了大量实验。 我们的主要两项结论是:(1) 完全在侧面、未加工和未受监督的训练前学习面部面部应用的两种方法。 在某些情况下,我们的评价侧重于少数面部学习的案例。 (c) 我们调查了培训数据集的准确性和重大程度。