Medical data often exhibits long-tail distributions with heavy class imbalance, which naturally leads to difficulty in classifying the minority classes (i.e., boundary regions or rare objects). Recent work has significantly improved semi-supervised medical image segmentation in long-tailed scenarios by equipping them with unsupervised contrastive criteria. However, it remains unclear how well they will perform in the labeled portion of data where class distribution is also highly imbalanced. In this work, we present ACTION++, an improved contrastive learning framework with adaptive anatomical contrast for semi-supervised medical segmentation. Specifically, we propose an adaptive supervised contrastive loss, where we first compute the optimal locations of class centers uniformly distributed on the embedding space (i.e., off-line), and then perform online contrastive matching training by encouraging different class features to adaptively match these distinct and uniformly distributed class centers. Moreover, we argue that blindly adopting a constant temperature $\tau$ in the contrastive loss on long-tailed medical data is not optimal, and propose to use a dynamic $\tau$ via a simple cosine schedule to yield better separation between majority and minority classes. Empirically, we evaluate ACTION++ on ACDC and LA benchmarks and show that it achieves state-of-the-art across two semi-supervised settings. Theoretically, we analyze the performance of adaptive anatomical contrast and confirm its superiority in label efficiency.

翻译：医学数据常呈现长尾分布且存在严重类别不平衡，这自然导致少数类别（如边界区域或罕见目标）的分类困难。近年研究通过为半监督医学图像分割配备无监督对比准则，显著提升了长尾场景下的分割性能。然而，当标注数据同样存在高度类别不平衡时，这些方法的有效性尚不明确。本文提出ACTION++——一种改进的具有自适应解剖对比的对比学习框架，用于半监督医学分割。具体而言，我们提出自适应监督对比损失：首先计算嵌入空间中均匀分布的类中心最优位置（离线方式），然后通过鼓励不同类别特征自适应匹配这些相互分离且均匀分布的类中心，进行在线对比匹配训练。此外，我们认为在长尾医学数据上盲目采用固定温度参数τ并非最优，提出通过简单余弦调度使用动态τ，以实现多数类与少数类之间的更好分离。实验表明，ACTION++在ACDC和LA基准测试中达到了两个半监督设置下的最优性能。理论上，我们分析了自适应解剖对比的性能，证实其在标签效率上的优越性。