通过图像合成与知识蒸馏，提升宫颈细胞病理跨机构检测准确率。
Two-Stage Cross-Domain Cervical Abnormality Screening with Cytopathological Image Synthesis and Knowledge Distillation
- 构建合成中间域，用熵正则化最优传输实现跨域图像转换。
- 双层特征对齐使浅层结构与深层语义特征逐步对齐。
- 适合医疗影像跨机构部署，尤其适用于数据分布差异大的场景。
由于不同医疗机构间存在显著的领域偏移，且疾病阶段间的视觉差异微弱，跨域宫颈细胞病理诊断面临重大挑战，严重影响模型泛化能力。为此，本文提出一种两阶段跨域宫颈细胞检测框架。第一阶段提出空间连续无配对神经薛定谔桥（SC-UNSB），将图像转换建模为熵正则化最优传输过程，构建合成中间域以缓解跨域分布偏移。第二阶段在知识蒸馏中引入双层特征对齐策略，逐步对齐浅层结构特征与深层语义表示，促进源域到目标域的域不变知识迁移。实验表明，该方法有效缓解领域偏移与类别模糊问题，显著提升跨域检测性能。
原文摘要 · Abstract (English)
Cross-domain diagnosis remains a major challenge in cervical cell pathology due to pronounced domain shifts across institutions and the subtle visual differences among disease stages, which jointly impair model generalization. To address these issues, this paper proposes a two-stage framework for cross-domain cervical cell detection. In the first stage, we propose the Spatially-Continuous Unpaired Neural Schrödinger Bridge (SC-UNSB), which constructs a synthetic intermediate domain to mitigate cross-domain distribution shifts by modeling image translation as an entropy-regularized optimal transport process. In the second stage, we propose a dual-level feature alignment strategy within a knowledge distillation, which progressively aligns shallow structural features and deep semantic representations to facilitate the transfer of domain-invariant knowledge from the source to the target model. Experimental results demonstrate that the proposed method effectively mitigates domain shift and category ambiguity, improving the cross-domain detection performance.
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。