SemiGDA：面向半监督医学图像分割的生成式双分布对齐
SemiGDA: Generative Dual-distribution Alignment for Semi-Supervised Medical Image Segmentation
用双编码器分别建模图像与掩码的特征分布，并在潜空间施加分布约束做对齐，这个思路可迁移到任何只有少量标注、需要特征级一致性正则的半监督密集预测任务；CDSA 的双跳跃适配器加一致性损失也是可直接复用的多尺度特征融合模块。
原文依据 enforces their alignment in the latent space via distributional constraints, establishing structured feature consistency
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论半监督学习通过挖掘无标注数据中的潜在信息来提升模型性能，从而缓解医学图像分割中的标注稀缺与标注成本高昂问题。传统的判别式分割依赖分割掩码，忽视了特征层面的分布约束，这在标注稀少的场景下限制了鲁棒的语义表征学习以及对无标注数据的自适应建模。为解决上述局限，我们提出 SemiGDA，一种用于半监督医学图像分割的新型生成式双分布对齐框架。SemiGDA 通过对齐特征分布与语义分布来促进语义学习和场景适应性，从而摆脱判别式方法对大规模标注数据集的依赖。具体而言，我们提出双分布对齐模块（DAM），它采用两个结构不同的编码器分别建模图像与掩码的特征分布，并通过分布约束在潜空间中强制二者对齐，从而建立结构化的特征一致性。此外，我们设计了一致性驱动的跳跃适配器（CDSA）策略，引入图像与掩码两个跳跃适配器，通过跳跃连接融合多尺度特征；CDSA 利用一致性损失增强跨分支的语义对齐，并强化细粒度的语义一致性。在多个医学数据集上的实验结果表明，我们的方法优于其他最优的半监督分割方法。代码已发布于：https://github.com/taozh2017/SemiGDA。
英文原文摘要 1562 字符
Semi-supervised learning addresses label scarcity and high annotation costs in medical image segmentation by exploiting the latent information in unlabeled data to enhance model performance. Traditional discriminative segmentation relies on segmentation masks, neglecting feature-level distribution constraints. This limits robust semantic representation learning and adaptive modeling of unlabeled data in scenarios with few labels. To address these limitations, we propose SemiGDA, a novel Generative Dual-distribution Alignment framework for semi-supervised medical image segmentation. Our SemiGDA overcomes the reliance of discriminative methods on large labeled datasets by aligning feature and semantic distributions to boost semantic learning and scene adaptability. Specifically, we propose a Dual-distribution Alignment Module (DAM), which employs two structurally distinct encoders to model image and mask feature distributions. It enforces their alignment in the latent space via distributional constraints, establishing structured feature consistency. Moreover, we design a Consistency-Driven Skip Adapter (CDSA) strategy, which introduces dual skip adapters (Image and Mask) to fuse multi-scale features via skip connections. Using a consistency loss, CDSA enhances cross-branch semantic alignment and reinforces fine-grained semantic consistency. Experimental results on diverse medical datasets show that our method outperforms other state-of-the-art semi-supervised segmentation methods. Code is released at: https://github.com/taozh2017/SemiGDA.