Model learning from class imbalanced training data is a long-standing and significant challenge for machine learning. In particular, existing deep learning methods consider mostly either class balanced data or moderately imbalanced data in model training, and ignore the challenge of learning from significantly imbalanced training data. To address this problem, we formulate a class imbalanced deep learning model based on batch-wise incremental minority (sparsely sampled) class rectification by hard sample mining in majority (frequently sampled) classes during model training. This model is designed to minimise the dominant effect of majority classes by discovering sparsely sampled boundaries of minority classes in an iterative batch-wise learning process. To that end, we introduce a Class Rectification Loss (CRL) function that can be deployed readily in deep network architectures. Extensive experimental evaluations are conducted on three imbalanced person attribute benchmark datasets (CelebA, X-Domain, DeepFashion) and one balanced object category benchmark dataset (CIFAR-100). These experimental results demonstrate the performance advantages and model scalability of the proposed batch-wise incremental minority class rectification model over the existing state-of-the-art models for addressing the problem of imbalanced data learning.

中文翻译：

---

少数族裔增量矫正导致的深度学习不平衡

从班级不平衡训练数据中进行模型学习是机器学习的一项长期而重大的挑战。特别是，现有的深度学习方法在模型训练中主要考虑类平衡数据或中度不平衡数据，而忽略了从严重失衡的训练数据中学习的挑战。为了解决这个问题，我们在模型训练过程中通过对大多数（经常采样）班级进行硬样本挖掘，基于批处理增量式少数（稀疏采样）班级校正，建立了基于班级不平衡的深度学习模型。该模型旨在通过在迭代的分批学习过程中发现少数群体的稀疏采样边界，来最大程度地减少多数群体的主导作用。为此，我们引入了一种类整流损失（CRL）功能，该功能可以很容易地部署在深度网络体系结构中。对三个不平衡的人属性基准数据集（CelebA，X-Domain，DeepFashion）和一个平衡的对象类别基准数据集（CIFAR-100）进行了广泛的实验评估。这些实验结果证明，与现有的解决数据学习不平衡问题的最新模型相比，所提出的批处理增量式少数类整流模型的性能优势和模型可伸缩性。