IEEE Trans Pattern Anal Mach Intell. 2020 Nov;42(11):2781-2794. doi: 10.1109/TPAMI.2019.2914680. Epub 2019 May 7.
Data for face analysis often exhibit highly-skewed class distribution, i.e., most data belong to a few majority classes, while the minority classes only contain a scarce amount of instances. To mitigate this issue, contemporary deep learning methods typically follow classic strategies such as class re-sampling or cost-sensitive training. In this paper, we conduct extensive and systematic experiments to validate the effectiveness of these classic schemes for representation learning on class-imbalanced data. We further demonstrate that more discriminative deep representation can be learned by enforcing a deep network to maintain inter-cluster margins both within and between classes. This tight constraint effectively reduces the class imbalance inherent in the local data neighborhood, thus carving much more balanced class boundaries locally. We show that it is easy to deploy angular margins between the cluster distributions on a hypersphere manifold. Such learned Cluster-based Large Margin Local Embedding (CLMLE), when combined with a simple k-nearest cluster algorithm, shows significant improvements in accuracy over existing methods on both face recognition and face attribute prediction tasks that exhibit imbalanced class distribution.
用于面部分析的数据通常表现出高度倾斜的类别分布，即大多数数据属于少数几个多数类别，而少数类别只包含少量实例。为了解决这个问题，当代深度学习方法通常采用经典策略，如类别重采样或代价敏感训练。在本文中，我们进行了广泛而系统的实验，以验证这些经典方案在类别不平衡数据上的表示学习的有效性。我们进一步证明，通过强制深度网络在类内和类间保持聚类间隔，可以学习到更具判别力的深度表示。这种严格的约束有效地减少了局部数据邻域中固有的类别不平衡，从而在局部产生更平衡的类别边界。我们表明，在超球流形上的聚类分布之间部署角距是很容易的。所学习的基于聚类的大间隔局部嵌入（CLMLE），当与简单的 K-最近聚类算法结合使用时，在具有类别不平衡分布的人脸识别和人脸属性预测任务中，与现有方法相比，在准确性方面有显著提高。
