IEEE Trans Pattern Anal Mach Intell. 2019 Jun;41(6):1367-1381. doi: 10.1109/TPAMI.2018.2832629. Epub 2018 May 3.
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.
从类别不平衡的训练数据中进行模型学习是机器学习中一个长期存在的重大挑战。特别是，现有的深度学习方法在模型训练中大多考虑类别平衡的数据或适度不平衡的数据，而忽略了从严重不平衡的训练数据中学习的挑战。为了解决这个问题，我们在模型训练期间通过在多数（频繁采样）类中进行硬样本挖掘，基于逐批增量少数（稀疏采样）类校正来构建一个类别不平衡深度学习模型。该模型旨在通过在迭代的逐批学习过程中发现少数类的稀疏采样边界，来最小化多数类的主导效应。为此，我们引入了一种可以在深度网络架构中轻松部署的类别校正损失（CRL）函数。我们在三个不平衡的人物属性基准数据集（CelebA、X-Domain、DeepFashion）和一个平衡的物体类别基准数据集（CIFAR-100）上进行了广泛的实验评估。这些实验结果证明了所提出的逐批增量少数类校正模型在解决不平衡数据学习问题上相对于现有最先进模型的性能优势和模型可扩展性。
