Class imbalance is a fundamental problem in computer vision applications such as semantic segmentation. Specifically, uneven class distributions in a training dataset often result in unsatisfactory performance on under-represented classes. Many works have proposed to weight the standard cross entropy loss function with pre-computed weights based on class statistics, such as the number of samples and class margins. There are two major drawbacks to these methods: 1) constantly up-weighting minority classes can introduce excessive false positives in semantic segmentation; 2) a minority class is not necessarily a hard class. The consequence is low precision due to excessive false positives. In this regard, we propose a hard-class mining loss by reshaping the vanilla cross entropy loss such that it weights the loss for each class dynamically based on instantaneous recall performance. We show that the novel recall loss changes gradually between the standard cross entropy loss and the inverse frequency weighted loss. Recall loss also leads to improved mean accuracy while offering competitive mean Intersection over Union (IoU) performance. On Synthia dataset, recall loss achieves 9% relative improvement on mean accuracy with competitive mean IoU using DeepLab-ResNet18 compared to the cross entropy loss. Code available at https://github.com/PotatoTian/recall-semseg.

本研究提出了一种基于瞬时召回表现动态加权的损失函数：hard-class mining loss，以解决计算机视觉应用程序（如语义分割）中的类别不平衡问题。研究结果表明，recall loss可以在不影响准确度的情况下提高平均准确度，并具有与标准交叉熵损失相竞争的平均Intersection over Union（IoU）性能。

在语义分割中实现平衡：召回损失