Concept shift is a prevailing problem in natural tasks like medical image segmentation where samples usually come from different subpopulations with variant correlations between features and labels. One common type of concept shift in medical image segmentation is the "information imbalance" between label-sparse samples with few (if any) segmentation labels and label-dense samples with plentiful labeled pixels. Existing distributionally robust algorithms have focused on adaptively truncating/down-weighting the "less informative" (i.e., label-sparse in our context) samples. To exploit data features of label-sparse samples more efficiently, we propose an adaptively weighted online optimization algorithm -- AdaWAC -- to incorporate data augmentation consistency regularization in sample reweighting. Our method introduces a set of trainable weights to balance the supervised loss and unsupervised consistency regularization of each sample separately. At the saddle point of the underlying objective, the weights assign label-dense samples to the supervised loss and label-sparse samples to the unsupervised consistency regularization. We provide a convergence guarantee by recasting the optimization as online mirror descent on a saddle point problem. Our empirical results demonstrate that AdaWAC not only enhances the segmentation performance and sample efficiency but also improves the robustness to concept shift on various medical image segmentation tasks with different UNet-style backbones.
翻译:在医学图像分割等自然任务中,概念转变是一个普遍的问题,例如医学图像分割,样本通常来自不同的亚群,具有特征和标签之间的不同相关性。在医学图像分割中,概念转变的一个常见类型是,在极少(如果有的话)分解标签和标签敏感样本之间,标签偏差样本与标签分解标签标签分解标签标签标签标签标签和标签标签标签像素之间“信息不平衡”是一个普遍的问题。现有的分布式强的算法侧重于适应性抽调/下加权“信息缺失”样本(即,我们背景中的标签偏差)样本。为更有效地利用标签采样和标签采集样本的数据特征,我们建议采用适应性加权在线优化算法 -- -- AdaWAC -- 将数据增强一致性正规化纳入样本再加权中。我们的方法引入了一套可训练的重量,以平衡每个样本受监督的损失和不受监督的一致性调节。在基本目标的顶端点,加权将标签偏差样本划为受监督的损失和标签提取样本样本的样本进行非监督一致性整整。我们通过重新配置优化的在线优化的在线优化的在线优化的在线优化来保证,而不是重新定位,也展示了我们系统测量了不同比例。