提出新框架提升医疗影像无监督域适应性能
One Size does not Fit All: Heterogeneous Latent Space Alignment for Unsupervised Domain Adaptation
- 用双编码器变分自编码器+连续流增强表征能力
- 通过不平衡最优传输对齐不同数据域，提升分割精度
- 结合对抗增强生成极端样本，适合医疗高风险场景
领域偏移仍是医疗等高风险场景中机器学习模型可靠部署的主要障碍。现有域自适应方法受限于潜在表示表达能力不足及依赖人工静态增强。本文提出面向医疗图像分割的新型无监督域适应深度学习架构ADualVUOT，融合双编码器变分自编码器（VAE）与连续归一化流（CNFs），提升建模灵活性和后验表达能力。为实现域对齐，采用基于高斯-格罗莫夫-沃瑟斯坦（GGW）距离的不平衡最优传输（UOT），有效处理域间结构与拓扑差异。此外，引入对抗性增强策略合成最差情况样本，增强模型鲁棒性。在多个医学影像基准上的实验表明，该方法显著优于以往基于最优传输的方法。
原文摘要 · Abstract (English)
Domain shift remains a major obstacle to the reliable deployment of machine learning models in high-stakes environments such as healthcare. While Domain adaptation aims to mitigate these effects, existing approaches suffer from limited expressiveness of latent representations and a reliance on handcrafted, static augmentations. In this work, we address these limitations by proposing a novel deep learning architecture for Unsupervised Domain Adaptation (UDA), specifically optimized for medical image segmentation. Our framework, ADualVUOT, integrates a dual-encoder Variational Autoencoder (VAE) with Continuous Normalizing Flows (CNFs) to increase modeling flexibility and posterior expressiveness. To achieve domain alignment, we leverage Unbalanced Optimal Transport (UOT) through the Gaussian-Gromov-Wasserstein (GGW) distance, which handles structural and topological discrepancies between domains. Furthermore, we incorporate an adversarial augmentation scheme to synthesize worst-case compositions, thus enhancing model robustness. Extensive experiments on medical imaging benchmarks show significant gains over prior OT-based approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。