In this work, we propose a simple yet effective method to tackle the problem of imbalanced multi-class semantic segmentation in deep learning systems. One of the key properties for a good training set is the balancing among the classes. When the input distribution is heavily imbalanced in the number of instances, the learning process could be hindered or difficult to carry on. To this end, we propose a Dynamic Label Injection (DLI) algorithm to impose a uniform distribution in the input batch. Our algorithm computes the current batch defect distribution and re-balances it by transferring defects using a combination of Poisson-based seamless image cloning and cut-paste techniques. A thorough experimental section on the Magnetic Tiles dataset shows better results of DLI compared to other balancing loss approaches also in the challenging weakly-supervised setup. The code is available at https://github.com/covisionlab/dynamic-label-injection.git

翻译：在本研究中，我们提出了一种简单而有效的方法来解决深度学习系统中不平衡多类语义分割的问题。良好训练集的关键特性之一在于类别间的平衡性。当输入数据在实例数量上呈现严重不平衡分布时，学习过程可能受阻或难以持续。为此，我们提出了动态标签注入（DLI）算法，在输入批次中强制实现均匀分布。该算法通过计算当前批次的缺陷分布，并采用基于泊松分布的无缝图像克隆与剪切粘贴技术相结合的方式转移缺陷，从而实现数据重平衡。在磁砖数据集上的全面实验表明，即使在具有挑战性的弱监督设置下，DLI相较于其他平衡损失方法仍能取得更优的结果。代码已发布于 https://github.com/covisionlab/dynamic-label-injection.git