Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models. The majority of research on training neural networks under class imbalance has focused on specialized loss functions, sampling techniques, or two-stage training procedures. Notably, we demonstrate that simply tuning existing components of standard deep learning pipelines, such as the batch size, data augmentation, optimizer, and label smoothing, can achieve state-of-the-art performance without any such specialized class imbalance methods. We also provide key prescriptions and considerations for training under class imbalance, and an understanding of why imbalance methods succeed or fail.
翻译:现实世界的数据集通常存在严重的类别不平衡问题,这可能会对深度学习模型的性能产生不利影响。针对类别不平衡下神经网络训练的大部分研究都集中在专门的损失函数、采样技术或两阶段训练流程上。值得注意的是,我们证明只需调整标准深度学习流程的现有组件(如批量大小、数据增强、优化器和标签平滑),就能在无需任何此类专门类别不平衡方法的情况下实现最先进的性能。我们还提供了在类别不平衡下训练的关键方案与考量因素,并深入理解了不平衡方法成功或失败的原因。