Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. The imbalance in the ratio of positive and negative samples for each class skews network output probabilities further from ground-truth distributions. We propose a method, Partial Label Masking (PLM), which utilizes this ratio during training. By stochastically masking labels during loss computation, the method balances this ratio for each class, leading to improved recall on minority classes and improved precision on frequent classes. The ratio is estimated adaptively based on the network's performance by minimizing the KL divergence between predicted and ground-truth distributions. Whereas most existing approaches addressing data imbalance are mainly focused on single-label classification and do not generalize well to the multi-label case, this work proposes a general approach to solve the long-tail data imbalance issue for multi-label classification. PLM is versatile: it can be applied to most objective functions and it can be used alongside other strategies for class imbalance. Our method achieves strong performance when compared to existing methods on both multi-label (MultiMNIST and MSCOCO) and single-label (imbalanced CIFAR-10 and CIFAR-100) image classification datasets.
翻译:以长期标签分发方式进行真实世界数据集培训的神经网络偏向于频繁的班级,在不常见的班级上表现不佳。每个班级的正和负样本比例不平衡,每个班级的基底网输出概率因地面图谱分布而进一步出现偏差。我们提出了一个方法,即部分标签遮罩(PLM),在培训期间使用这个比例。在计算损失时,通过擦拭掩码标签,方法平衡了每个班级的这一比率,从而改善了少数族裔班级的召回,提高了频繁班级的精确度。该比率是根据网络的性能,通过尽量减少预测和地面图谱分布之间的 KL差异,根据网络的性能进行适应性估算。虽然大多数解决数据不平衡的现有方法主要侧重于单标签分类,而且没有很好地概括多标签案例,但这项工作提出了解决多标签分类中长尾数据不平衡问题的一般方法。PLMMM:它可以适用于最客观的功能,并且可以与其他班级不平衡的战略一起使用。我们的方法在与现有方法相比,在多标签(MtiMILIS-10)和(IAR-10)图像(IMIS-IAR-ILAS-IAS-IAS-10)的现有方法(MIS-IAS-10)上,我们的方法实现了强性)。