Although binary classification is a well-studied problem in computer vision, training reliable classifiers under severe class imbalance remains a challenging problem. Recent work has proposed techniques that mitigate the effects of training under imbalance by modifying the loss functions or optimization methods. While this work has led to significant improvements in the overall accuracy in the multi-class case, we observe that slight changes in hyperparameter values of these methods can result in highly variable performance in terms of Receiver Operating Characteristic (ROC) curves on binary problems with severe imbalance. To reduce the sensitivity to hyperparameter choices and train more general models, we propose training over a family of loss functions, instead of a single loss function. We develop a method for applying Loss Conditional Training (LCT) to an imbalanced classification problem. Extensive experiment results, on both CIFAR and Kaggle competition datasets, show that our method improves model performance and is more robust to hyperparameter choices. Code will be made available at: https://github.com/klieberman/roc_lct.

翻译：尽管二分类是计算机视觉中研究较充分的问题，但在严重类别不平衡条件下训练可靠分类器仍具挑战性。近期研究通过改进损失函数或优化方法提出了缓解不平衡训练影响的若干技术。虽然这些工作在多分类任务中显著提升了整体准确率，但我们发现这些方法超参数值的细微变化会导致严重不平衡二分类问题的接收者操作特征（ROC）曲线产生高度变异性能。为降低对超参数选择的敏感性并训练更通用的模型，我们提出采用损失函数族而非单一损失函数进行训练。我们开发了将损失条件训练（LCT）应用于不平衡分类问题的方法。在CIFAR和Kaggle竞赛数据集上的大量实验结果表明，本方法能够提升模型性能并增强对超参数选择的鲁棒性。代码将在以下网址开源：https://github.com/klieberman/roc_lct。