Abstract
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.
Abstract (translated)
人脸分析的数据通常表现出高度偏斜的类分布，即大多数数据属于少数多数类，而少数类仅包含少量实例。为了缓解这一问题，当代的深度学习方法通常遵循经典的策略，如课堂重新抽样或成本敏感的培训。本文通过大量的系统实验，验证了这些经典的表示学习方法对不平衡数据的有效性。我们进一步证明，通过实施一个深层网络来维护类内和类间的集群间边界，可以学习到更具歧视性的深层表示。这种严格的约束有效地减少了本地数据邻域中固有的类不平衡，从而在本地划分出更加平衡的类边界。我们证明了在超球面流形上，在星团分布之间很容易部署角边界。这种基于学习聚类的大边缘局部嵌入（CLMLE）与一种简单的k-最近聚类算法相结合，在人脸识别和人脸属性预测任务中显示出与现有方法相比的显著精度提高，这些任务显示出不平衡的类分布。
URL
https://arxiv.org/abs/1806.00194
