论文标题
边界感知的信息最大化，用于自我监督的医学图像细分
Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation
论文作者
论文摘要
在标记有限的数据下，无监督的预培训已被证明是一种有效的方法来提高各种下游任务。在各种方法中，对比学习通过构建正面和负面对学习歧视性表示。但是，以无监督的方式为分割任务构建合理的对并不是一件容易的事。在这项工作中，我们提出了一个新颖的无监督的预训练框架，以避免对比度学习的缺点。我们的框架包括两个原则：使用共同信息最大化和边界意识保存学习的无监督过度分割作为预训练的任务。两个基准的医学分割数据集的实验结果揭示了我们方法在很少的带注释的图像时提高分割性能的有效性。
Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and negative pairs. However, it is not trivial to build reasonable pairs for a segmentation task in an unsupervised way. In this work, we propose a novel unsupervised pre-training framework that avoids the drawback of contrastive learning. Our framework consists of two principles: unsupervised over-segmentation as a pre-train task using mutual information maximization and boundary-aware preserving learning. Experimental results on two benchmark medical segmentation datasets reveal our method's effectiveness in improving segmentation performance when few annotated images are available.
